Daily Papers

Remote sensing multimodal large language models (RS-MLLMs) have improved general aerial-image understanding. However, Earth observation applications require fine-grained scenario specialization, constrained by scarce high-quality scenario data and incomplete capability coverage. We formulate this adaptation as a capability-gap-driven post-training problem and propose filling before advancing (FBA). Rather than relying on single-stage supervised fine-tuning (SFT) over target-domain samples, FBA first fills prerequisite capability gaps before advancing toward scenario specialization. We instantiate FBA for coastal harbor understanding, a representative multi-source scenario, by constructing CPRS (Coastal-Port Remote Sensing), a three-layer supervision dataset coupled with three ordered stages: (1) RS semantic anchoring for overhead-view visual-language alignment; (2) domain-bridge convergence for shared RS priors across target and bridging scenarios under different modalities; and (3) evidence-grounded scenario tuning for downstream performance. We construct HarborEval, an eight-track diagnostic benchmark covering perception, spatial understanding, robustness, and generation. Under comparable training budgets, HarborEval increases from 57.95 with Direct-SFT to 70.29 with FBA on LLaVA-v1.5, and from 81.09 to 83.37 on Qwen3-VL. FBA also outperforms Collapsed-SFT and leads on harbor-related VRSBench/RSVQA subsets and OpenEval. Stage-wise and role-replacement analyses validate progressive gap filling and stage-specific roles. Public examples and release updates for CPRS, HarborEval, code, and trained weights are available at https://github.com/Z0ngL1ng/filling-before-advancing.

Conventional evaluation methods for multimodal LLMs (MLLMs) lack interpretability and are often insufficient to fully disclose significant capability gaps across models. To address this, we introduce AuditDM, an automated framework that actively discovers and rectifies MLLM failure modes by auditing their divergence. AuditDM fine-tunes an MLLM as an auditor via reinforcement learning to generate challenging questions and counterfactual images that maximize disagreement among target models. Once trained, the auditor uncovers diverse, interpretable exemplars that reveal model weaknesses and serve as annotation-free data for rectification. When applied to SoTA models like Gemma-3 and PaliGemma-2, AuditDM discovers more than 20 distinct failure types. Fine-tuning on these discoveries consistently improves all models across 16 benchmarks, and enables a 3B model to surpass its 28B counterpart. Our results suggest that as data scaling hits diminishing returns, targeted model auditing offers an effective path to model diagnosis and improvement.

Majority voting over multiple LLM attempts improves mathematical reasoning, but correlated errors limit the effective sample size. A natural fix is to assign different reasoning strategies to different voters. The approach, Diverse Prompt Mixer, is tested on the AIMO 3 competition: 3 models, 23+ experiments, 50 IMO-level problems, one H100 80 GB, 5-hour limit. Every prompt-level intervention fails. High-temperature sampling already decorrelates errors; weaker strategies reduce accuracy more than they reduce correlation. Across an 8-point capability gap at equal N=8 and every optimization tested, model capability dominates. The gap between the best majority-vote score (42/50) and pass@20 (~45.5) is selection loss, not prompt loss. A verifier-based selector could close it. Prompt engineering cannot.

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully solving a subset of tasks in the environment. Many existing approaches either rely on synthetic training data that is not targeted to the model's actual capability deficits in the target environment or train directly on the target environment, where the model needs to implicitly learn the capabilities across tasks. We introduce TRACE (Turning Recurrent Agent failures into Capability-targeted training Environments), an end-to-end system for environment-specific agent self-improvement. TRACE contrasts successful and failed trajectories to automatically identify lacking capabilities, synthesizes a targeted training environment for each that rewards whether the capability was exercised, and trains a LoRA adapter via RL on each synthetic environment, routing to the relevant adapter at inference. Empirically, TRACE generalizes across different environments, improving over the base agent by +14.1 points on τ^2-bench (customer service) and +7 perfect scores on ToolSandbox (tool use), outperforming the strongest baseline by +7.4 points and +4 perfect scores, respectively. Given the same number of rollouts, TRACE scales more efficiently than baselines, outperforming GRPO and GEPA by +9.2 and +7.4 points on τ^2-bench.

As large language models grow in capability and agency, identifying vulnerabilities through red-teaming becomes vital for safe deployment. However, traditional prompt-engineering approaches may prove ineffective once red-teaming turns into a weak-to-strong problem, where target models surpass red-teamers in capabilities. To study this shift, we frame red-teaming through the lens of the capability gap between attacker and target. We evaluate more than 500 attacker-target pairs using LLM-based jailbreak attacks that mimic human red-teamers across diverse families, sizes, and capability levels. Three strong trends emerge: (i) more capable models are better attackers, (ii) attack success drops sharply once the target's capability exceeds the attacker's, and (iii) attack success rates correlate with high performance on social science splits of the MMLU-Pro benchmark. From these trends, we derive a jailbreaking scaling law that predicts attack success for a fixed target based on attacker-target capability gap. These findings suggest that fixed-capability attackers (e.g., humans) may become ineffective against future models, increasingly capable open-source models amplify risks for existing systems, and model providers must accurately measure and control models' persuasive and manipulative abilities to limit their effectiveness as attackers.

Visual grounding, localizing objects from natural language descriptions, represents a critical bridge between language and vision understanding. While multimodal large language models (MLLMs) achieve impressive scores on existing benchmarks, a fundamental question remains: can MLLMs truly ground language in vision with human-like sophistication, or are they merely pattern-matching on simplified datasets? Current benchmarks fail to capture real-world complexity where humans effortlessly navigate ambiguous references and recognize when grounding is impossible. To rigorously assess MLLMs' true capabilities, we introduce GroundingME, a benchmark that systematically challenges models across four critical dimensions: (1) Discriminative, distinguishing highly similar objects, (2) Spatial, understanding complex relational descriptions, (3) Limited, handling occlusions or tiny objects, and (4) Rejection, recognizing ungroundable queries. Through careful curation combining automated generation with human verification, we create 1,005 challenging examples mirroring real-world complexity. Evaluating 25 state-of-the-art MLLMs reveals a profound capability gap: the best model achieves only 45.1% accuracy, while most score 0% on rejection tasks, reflexively hallucinating objects rather than acknowledging their absence, raising critical safety concerns for deployment. We explore two strategies for improvements: (1) test-time scaling selects optimal response by thinking trajectory to improve complex grounding by up to 2.9%, and (2) data-mixture training teaches models to recognize ungroundable queries, boosting rejection accuracy from 0% to 27.9%. GroundingME thus serves as both a diagnostic tool revealing current limitations in MLLMs and a roadmap toward human-level visual grounding.

Qwen3-8B reviewing Llama-3.1-8B in math adds 33.2 points, yet Qwen3-8B alone is 6.4 points more accurate than the result. Reviewing another model's answer is usually judged by its gain over the generator. We show that this confuses verification, which adds accuracy beyond either model alone, with capability transfer, where a stronger reviewer supplies answers it could have given on its own. Measured against the stronger model alone, across 48 pairs of 12 open-weight models (3B to 72B) in math, knowledge, code and reasoning, review beats it in only 9 of 96 review directions, and does worse the larger the capability gap. The reason is that the reviewer mostly follows the generator, discarding its own correct answers. Review costs 2.6 to 2.8 times as much as the stronger model alone, while a selector using the same two calls is 2.7 to 4.2 points more accurate than review and cheaper. Studies of verification should report the stronger model alone, not only the gain over the generator. Code and per-question results: https://github.com/Kamilaabb/verification-or-capability-transfer

In this report, we introduce InternVL 1.5, an open-source multimodal large language model (MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. We introduce three simple improvements: (1) Strong Vision Encoder: we explored a continuous learning strategy for the large-scale vision foundation model -- InternViT-6B, boosting its visual understanding capabilities, and making it can be transferred and reused in different LLMs. (2) Dynamic High-Resolution: we divide images into tiles ranging from 1 to 40 of 448times448 pixels according to the aspect ratio and resolution of the input images, which supports up to 4K resolution input. (3) High-Quality Bilingual Dataset: we carefully collected a high-quality bilingual dataset that covers common scenes, document images, and annotated them with English and Chinese question-answer pairs, significantly enhancing performance in OCR- and Chinese-related tasks. We evaluate InternVL 1.5 through a series of benchmarks and comparative studies. Compared to both open-source and proprietary models, InternVL 1.5 shows competitive performance, achieving state-of-the-art results in 8 of 18 benchmarks. Code has been released at https://github.com/OpenGVLab/InternVL.

The capability gap between open-source and closed-source large language models (LLMs) remains a challenge in text-to-SQL tasks. In this paper, we introduce a synthetic data approach that combines data produced by larger, more powerful models (strong models) with error information data generated by smaller, not well-aligned models (weak models). The method not only enhances the domain generalization of text-to-SQL models but also explores the potential of error data supervision through preference learning. Furthermore, we employ the synthetic data approach for instruction tuning on open-source LLMs, resulting SENSE, a specialized text-to-SQL model. The effectiveness of SENSE is demonstrated through state-of-the-art results on the SPIDER and BIRD benchmarks, bridging the performance gap between open-source models and methods prompted by closed-source models.

Despite the recent successes of vanilla Graph Neural Networks (GNNs) on many tasks, their foundation on pairwise interaction networks inherently limits their capacity to discern latent higher-order interactions in complex systems. To bridge this capability gap, we propose a novel approach exploiting the rich mathematical theory of simplicial complexes (SCs) - a robust tool for modeling higher-order interactions. Current SC-based GNNs are burdened by high complexity and rigidity, and quantifying higher-order interaction strengths remains challenging. Innovatively, we present a higher-order Flower-Petals (FP) model, incorporating FP Laplacians into SCs. Further, we introduce a Higher-order Graph Convolutional Network (HiGCN) grounded in FP Laplacians, capable of discerning intrinsic features across varying topological scales. By employing learnable graph filters, a parameter group within each FP Laplacian domain, we can identify diverse patterns where the filters' weights serve as a quantifiable measure of higher-order interaction strengths. The theoretical underpinnings of HiGCN's advanced expressiveness are rigorously demonstrated. Additionally, our empirical investigations reveal that the proposed model accomplishes state-of-the-art (SOTA) performance on a range of graph tasks and provides a scalable and flexible solution to explore higher-order interactions in graphs.

We introduce WebGames, a comprehensive benchmark suite designed to evaluate general-purpose web-browsing AI agents through a collection of 50+ interactive challenges. These challenges are specifically crafted to be straightforward for humans while systematically testing the limitations of current AI systems across fundamental browser interactions, advanced input processing, cognitive tasks, workflow automation, and interactive entertainment. Our framework eliminates external dependencies through a hermetic testing environment, ensuring reproducible evaluation with verifiable ground-truth solutions. We evaluate leading vision-language models including GPT-4o, Claude Computer-Use, Gemini-1.5-Pro, and Qwen2-VL against human performance. Results reveal a substantial capability gap, with the best AI system achieving only 43.1% success rate compared to human performance of 95.7%, highlighting fundamental limitations in current AI systems' ability to handle common web interaction patterns that humans find intuitive. The benchmark is publicly available at webgames.convergence.ai, offering a lightweight, client-side implementation that facilitates rapid evaluation cycles. Through its modular architecture and standardized challenge specifications, WebGames provides a robust foundation for measuring progress in development of more capable web-browsing agents.

Large language models (LLMs) achieve remarkable performance in code generation tasks. However, a significant performance disparity persists between popular programming languages (e.g., Python, C++) and others. To address this capability gap, we leverage the code translation task to train LLMs, thereby facilitating the transfer of coding proficiency across diverse programming languages. Moreover, we introduce OORL for training, a novel reinforcement learning (RL) framework that integrates on-policy and off-policy strategies. Within OORL, on-policy RL is applied during code translation, guided by a rule-based reward signal derived from unit tests. Complementing this coarse-grained rule-based reward, we propose Group Equivalent Preference Optimization (GEPO), a novel preference optimization method. Specifically, GEPO trains the LLM using intermediate representations (IRs) groups. LLMs can be guided to discern IRs equivalent to the source code from inequivalent ones, while also utilizing signals about the mutual equivalence between IRs within the group. This process allows LLMs to capture nuanced aspects of code functionality. By employing OORL for training with code translation tasks, LLMs improve their recognition of code functionality and their understanding of the relationships between code implemented in different languages. Extensive experiments demonstrate that our OORL for LLMs training with code translation tasks achieves significant performance improvements on code benchmarks across multiple programming languages.

In recent years, the research focus of large language models (LLMs) and agents has shifted increasingly from demonstrating novel capabilities to complex reasoning and tackling challenging tasks. However, existing evaluations focus mainly on math/code contests or general tasks, while existing multi-domain academic benchmarks lack sufficient reasoning depth, leaving the field without a rigorous benchmark for high-level reasoning. To fill this gap, we introduce the Acadreason benchmark, designed to evaluate the ability of LLMs and agents to acquire and reason over academic knowledge. It consists of 50 expert-annotated academic problems across five high-reasoning domains, including computer science, economics, law, mathematics, and philosophy. All questions are sourced from top-tier publications in recent years and undergo rigorous annotation and quality control to ensure they are both challenging and answerable. We conduct systematic evaluations of over 10 mainstream LLMs and agents. The results show that most LLMs scored below 20 points, with even the cutting-edge GPT-5 achieving only 16 points. While agents achieved higher scores, none exceeded 40 points. This demonstrates the current capability gap between LLMs and agents in super-intelligent academic research tasks and highlights the challenges of Acadreason.

Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts. However, a critical bottleneck remains: while agents have access to this context, their static prompts lack the mechanisms to manage it effectively, leading to recurring Corrective and Enhancement failures. To address this capability gap, we introduce SCOPE (Self-evolving Context Optimization via Prompt Evolution). SCOPE frames context management as an online optimization problem, synthesizing guidelines from execution traces to automatically evolve the agent's prompt. We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles). Furthermore, we introduce Perspective-Driven Exploration to maximize strategy coverage, increasing the likelihood that the agent has the correct strategy for any given task. Experiments on the HLE benchmark show that SCOPE improves task success rates from 14.23\% to 38.64\% without human intervention. We make our code publicly available at https://github.com/JarvisPei/SCOPE.

Sparse linear models are one of several core tools for interpretable machine learning, a field of emerging importance as predictive models permeate decision-making in many domains. Unfortunately, sparse linear models are far less flexible as functions of their input features than black-box models like deep neural networks. With this capability gap in mind, we study a not-uncommon situation where the input features dichotomize into two groups: explanatory features, which are candidates for inclusion as variables in an interpretable model, and contextual features, which select from the candidate variables and determine their effects. This dichotomy leads us to the contextual lasso, a new statistical estimator that fits a sparse linear model to the explanatory features such that the sparsity pattern and coefficients vary as a function of the contextual features. The fitting process learns this function nonparametrically via a deep neural network. To attain sparse coefficients, we train the network with a novel lasso regularizer in the form of a projection layer that maps the network's output onto the space of ell_1-constrained linear models. An extensive suite of experiments on real and synthetic data suggests that the learned models, which remain highly transparent, can be sparser than the regular lasso without sacrificing the predictive power of a standard deep neural network.

Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementary but underexplored setting through the lens of intrinsic risk, where intrinsic failures remain latent, propagate across long-horizon execution, and eventually lead to high-consequence outcomes. To evaluate this setting, we introduce non-attack intrinsic risk auditing and present HINTBench, a benchmark of 629 agent trajectories (523 risky, 106 safe; 33 steps on average) supporting three tasks: risk detection, risk-step localization, and intrinsic failure-type identification. Its annotations are organized under a unified five-constraint taxonomy. Experiments reveal a substantial capability gap: strong LLMs perform well on trajectory-level risk detection, but their performance drops to below 35 Strict-F1 on risk-step localization, while fine-grained failure diagnosis proves even harder. Existing guard models transfer poorly to this setting. These findings establish intrinsic risk auditing as an open challenge for agent safety.

Existing benchmarks for frontier models often test specialized, ``PhD-level'' knowledge that is difficult for non-experts to grasp. In contrast, we present a benchmark based on the NPR Sunday Puzzle Challenge that requires only general knowledge. Our benchmark is challenging for both humans and models, however correct solutions are easy to verify, and models' mistakes are easy to spot. Our work reveals capability gaps that are not evident in existing benchmarks: OpenAI o1 significantly outperforms other reasoning models that are on par on benchmarks that test specialized knowledge. Furthermore, our analysis of reasoning outputs uncovers new kinds of failures. DeepSeek R1, for instance, often concedes with ``I give up'' before providing an answer that it knows is wrong. R1 can also be remarkably ``uncertain'' in its output and in rare cases, it does not ``finish thinking,'' which suggests the need for an inference-time technique to ``wrap up'' before the context window limit is reached. We also quantify the effectiveness of reasoning longer with R1 and Gemini Thinking to identify the point beyond which more reasoning is unlikely to improve accuracy on our benchmark.

The accelerating development of general medical artificial intelligence (GMAI), powered by multimodal large language models (MLLMs), offers transformative potential for addressing persistent healthcare challenges, including workforce deficits and escalating costs. The parallel development of systematic evaluation benchmarks emerges as a critical imperative to enable performance assessment and provide technological guidance. Meanwhile, as an invaluable knowledge source, the potential of medical textbooks for benchmark development remains underexploited. Here, we present MedBookVQA, a systematic and comprehensive multimodal benchmark derived from open-access medical textbooks. To curate this benchmark, we propose a standardized pipeline for automated extraction of medical figures while contextually aligning them with corresponding medical narratives. Based on this curated data, we generate 5,000 clinically relevant questions spanning modality recognition, disease classification, anatomical identification, symptom diagnosis, and surgical procedures. A multi-tier annotation system categorizes queries through hierarchical taxonomies encompassing medical imaging modalities (42 categories), body anatomies (125 structures), and clinical specialties (31 departments), enabling nuanced analysis across medical subdomains. We evaluate a wide array of MLLMs, including proprietary, open-sourced, medical, and reasoning models, revealing significant performance disparities across task types and model categories. Our findings highlight critical capability gaps in current GMAI systems while establishing textbook-derived multimodal benchmarks as essential evaluation tools. MedBookVQA establishes textbook-derived benchmarking as a critical paradigm for advancing clinical AI, exposing limitations in GMAI systems while providing anatomically structured performance metrics across specialties.

Large language models (LLMs) have demonstrated excellent capabilities in generating structured diagrams from natural language descriptions. In particular, they have shown great promise in generating sequence diagrams for software engineering, typically represented in a text-based syntax such as Mermaid. However, systematic evaluations in this space remain underdeveloped as there is a lack of existing benchmarks to assess the LLM's correctness in this task. To address this shortcoming, we introduce MermaidSeqBench, a human-verified and LLM-synthetically-extended benchmark for assessing an LLM's capabilities in generating Mermaid sequence diagrams from textual prompts. The benchmark consists of a core set of 132 samples, starting from a small set of manually crafted and verified flows. These were expanded via a hybrid methodology combining human annotation, in-context LLM prompting, and rule-based variation generation. Our benchmark uses an LLM-as-a-judge model to assess Mermaid sequence diagram generation across fine-grained metrics, including syntax correctness, activation handling, error handling, and practical usability. We perform initial evaluations on numerous state-of-the-art LLMs and utilize multiple LLM judge models to demonstrate the effectiveness and flexibility of our benchmark. Our results reveal significant capability gaps across models and evaluation modes. Our proposed benchmark provides a foundation for advancing research in structured diagram generation and for developing more rigorous, fine-grained evaluation methodologies.

We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent scaffold, on a large university network consisting of ~8,000 hosts across 12 subnets. ARTEMIS is a multi-agent framework featuring dynamic prompt generation, arbitrary sub-agents, and automatic vulnerability triaging. In our comparative study, ARTEMIS placed second overall, discovering 9 valid vulnerabilities with an 82% valid submission rate and outperforming 9 of 10 human participants. While existing scaffolds such as Codex and CyAgent underperformed relative to most human participants, ARTEMIS demonstrated technical sophistication and submission quality comparable to the strongest participants. We observe that AI agents offer advantages in systematic enumeration, parallel exploitation, and cost -- certain ARTEMIS variants cost 18/hour versus 60/hour for professional penetration testers. We also identify key capability gaps: AI agents exhibit higher false-positive rates and struggle with GUI-based tasks.

Recent advances in image generation models have expanded their applications beyond aesthetic imagery toward practical visual content creation. However, existing benchmarks mainly focus on natural image synthesis and fail to systematically evaluate models under the structured and multi-constraint requirements of real-world commercial design tasks. In this work, we introduce BizGenEval, a systematic benchmark for commercial visual content generation. The benchmark spans five representative document types: slides, charts, webpages, posters, and scientific figures, and evaluates four key capability dimensions: text rendering, layout control, attribute binding, and knowledge-based reasoning, forming 20 diverse evaluation tasks. BizGenEval contains 400 carefully curated prompts and 8000 human-verified checklist questions to rigorously assess whether generated images satisfy complex visual and semantic constraints. We conduct large-scale benchmarking on 26 popular image generation systems, including state-of-the-art commercial APIs and leading open-source models. The results reveal substantial capability gaps between current generative models and the requirements of professional visual content creation. We hope BizGenEval serves as a standardized benchmark for real-world commercial visual content generation.

As the capability frontier of autonomous agents continues to expand, they are increasingly able to complete specialized tasks through plug-and-play external skills. Yet current benchmarks mostly test whether models can use provided skills, leaving open whether they can discover skills from experience, repair them after failure, and maintain a coherent library over time. We introduce SkillFlow, a benchmark of 166 tasks across 20 families in which task construction within each family follows a Domain-Agnostic Execution Flow (DAEF) that defines an agent workflow framework, allowing these tasks to share a consistent workflow. Agents are evaluated under an Agentic Lifelong Learning protocol in which they begin without skills, solve tasks sequentially within each family, externalize lessons through trajectory- and rubric-driven skill patches, and carry the updated library forward. Experiments reveal a substantial capability gap. For Claude Opus 4.6, lifelong skill evolution improves task success from 62.65% to 71.08% (+8.43 points). However, high skill usage does not necessarily imply high utility: Kimi K2.5 gains only +0.60 points despite 66.87% skill usage, while Qwen-Coder-Next reaches only a 44.58% task completion rate and still regresses relative to the vanilla setting. SkillFlow contributes a structured testbed for this direction and an in-depth empirical analysis of skill discovery, patching, transfer, and their failure modes under lifelong evaluation.

It is tempting to assume any task solvable by a short program can be taught to a model as its chain-of-thought: write the steps out, fine-tune, and the model follows. This paper shows the assumption fails for an identifiable class of procedures. The testbed is nine reasoning tasks, each from a deterministic generator; public and hidden splits share generators, so held-out data proxies test accuracy. I reverse-engineer the generators into Python solvers, render them as chain-of-thought, and distill into a rank-<= 32 LoRA over a 30B (3.5B-active) Nemotron model. Forward-computable tasks install readily: lookup/arithmetic and an 8-bit boolean task transfer (>= 0.99 and 0.68). Cryptarithm does not: distilling its backtracking search holds at 0.01-0.07 across eleven chain-of-thought designs, RL from verifiable rewards, and self-training, even though a search solver answers 71% of instances. This is not a capability gap. The model does the arithmetic on 97-100% of lines and ranks the correct cipher in its top eight on 71%; it cannot carry the search forward as a left-to-right derivation. Fine-tuning learns the shape of a verifiable elimination step while its verdicts become unconditional templates, correct only 16-57% of the time ("verdict-as-token"). The ceiling holds across backbones from 3B to 671B and across fine-tuning and prompting; a controlled intervention isolates the cause: revealing the cipher key, which turns the derivation forward, lifts the same instances from 0.03 to 0.57. When a procedure's only solution is search over information-free structure, no faithful forward chain-of-thought exists to imitate. The task becomes learnable only by removing the search, precomputing its combinatorial core into a catalog and reducing the trace to recall plus verification; the 1st-place solution reaches Private LB 0.92 this way. What distills is memorization and verification, not search.

A foundation model should not act in isolation as an embodied agent. Yet, existing methods often optimize individual components of the agent stack, such as memory, context, skills, or action interfaces, rather than treating the supporting system itself as a unified policy. Moreover, interaction alone does not yield self-improvement unless execution experience is converted into persistent, validated system changes. We therefore propose RoboFoundry, the first embodied agentic framework that formulates this process as Self-Evolving System-as-Policy. RoboFoundry diagnoses capability gaps in decision-making and memory management, converts execution traces into validated task-specific system updates, and promotes recurring improvements to the general system. Evolution operates over two complementary surfaces: a context system that manages active internal context and persistent file-system memory, and a hierarchical skill system that organizes atomic skills, reusable compositions, and failure-conditioned recovery. A shared semantic interface separates embodiment-invariant decisions from embodiment-specific execution, allowing evolved system capabilities to transfer across heterogeneous robots. On EmbodiedBench, RoboFoundry achieves state-of-the-art performance, notably improving GPT-5.5 by 27.8%. It also brings Qwen3.7-Plus to near parity with GPT-5.5 (70.3% vs. 72.7%), showing consistent gains from system-as-policy evolution across foundation models. For long-horizon memory, RoboFoundry outperforms all baselines on RoboMemArena by at least 39.0%, even against methods assisted by external foundation models. On LIBERO-PRO, it further outperforms Cap-Agent0 by 243.8%-679.7% across all perturbation types. In real-world deployments, RoboFoundry demonstrates zero-shot transfer and online evolution across robots and tasks, highlighting its potential for fully autonomous embodied agents.

Cumulative culture enables humans to preserve, reuse, and extend knowledge and skills across experiences and generations. Inspired by this principle, we introduce SimSkill, a self-evolving agent built around the Simulation of Urban MObility (SUMO) traffic simulator. SimSkill continually identifies capability gaps, generates and solves environment-grounded tasks, verifies solutions through an action--critic loop, and consolidates experience into episodic, procedural, and semantic memory. Through autonomous exploration, it builds a library of reusable skills and knowledge spanning major stages of the traffic-simulation workflow. We evaluate SimSkill on two held-out benchmarks across three backbone LLMs, with each result independently verified. It improves verified success by up to 25 percentage points, and ablations show complementary contributions from procedural and semantic memory. Its benefits remain backbone- and budget-dependent, as memory does not improve every model or uniformly reduce inference cost. More broadly, SimSkill illustrates a natural-language-centered design paradigm for LLM-based agent systems. Its high-level control logic, operating principles, and accumulated knowledge are expressed in natural language, while an LLM integrates them with executable tools and code to realize precise and reproducible execution. All code and experimental data are publicly available at https://github.com/qiliuchn/SimSkill-V1.

The integration of Multimodal Large Language Models (MLLMs) into chemistry promises to revolutionize scientific discovery, yet their ability to comprehend the dense, graphical language of reactions within authentic literature remains underexplored. Here, we introduce RxnBench, a multi-tiered benchmark designed to rigorously evaluate MLLMs on chemical reaction understanding from scientific PDFs. RxnBench comprises two tasks: Single-Figure QA (SF-QA), which tests fine-grained visual perception and mechanistic reasoning using 1,525 questions derived from 305 curated reaction schemes, and Full-Document QA (FD-QA), which challenges models to synthesize information from 108 articles, requiring cross-modal integration of text, schemes, and tables. Our evaluation of MLLMs reveals a critical capability gap: while models excel at extracting explicit text, they struggle with deep chemical logic and precise structural recognition. Notably, models with inference-time reasoning significantly outperform standard architectures, yet none achieve 50\% accuracy on FD-QA. These findings underscore the urgent need for domain-specific visual encoders and stronger reasoning engines to advance autonomous AI chemists.

As Large Language Model (LLM) alignment evolves from simple completions to complex, highly sophisticated generation, Reward Models are increasingly shifting toward rubric-guided evaluation to mitigate surface-level biases. However, the community lacks a unified benchmark to assess this evaluation paradigm, as existing benchmarks lack both the discriminative complexity and the ground-truth rubric annotations required for rigorous analysis. To bridge this gap, we introduce RubricBench, a curated benchmark with 1,147 pairwise comparisons specifically designed to assess the reliability of rubric-based evaluation. Our construction employs a multi-dimensional filtration pipeline to target hard samples featuring nuanced input complexity and misleading surface bias, augmenting each with expert-annotated, atomic rubrics derived strictly from instructions. Comprehensive experiments reveal a substantial capability gap between human-annotated and model-generated rubrics, indicating that even state-of-the-art models struggle to autonomously specify valid evaluation criteria, lagging considerably behind human-guided performance.

Current benchmarks for code agents primarily assess narrow, repository-specific fixes, overlooking critical real-world challenges such as cross-repository reasoning, domain-specialized problem solving, dependency-driven migration, and full-repository generation. To address this gap, we introduce BeyondSWE, a comprehensive benchmark that broadens existing evaluations along two axes - resolution scope and knowledge scope - using 500 real-world instances across four distinct settings. Experimental results reveal a significant capability gap: even frontier models plateau below 45% success, and no single model performs consistently across task types. To systematically investigate the role of external knowledge, we develop SearchSWE, a framework that integrates deep search with coding abilities. Our experiments show that search augmentation yields inconsistent gains and can in some cases degrade performance, highlighting the difficulty of emulating developer-like workflows that interleave search and reasoning during coding tasks. This work offers both a realistic, challenging evaluation benchmark and a flexible framework to advance research toward more capable code agents.

Small object-centric spatial understanding in indoor videos remains a significant challenge for multimodal large language models (MLLMs), despite its practical value for object search and assistive applications. Although existing benchmarks have advanced video spatial intelligence, embodied reasoning, and diagnostic perception, no existing benchmark directly evaluates whether a model can localize a target object in video and express its position with sufficient precision for downstream use. In this work, we introduce PinpointQA, the first dataset and benchmark for small object-centric spatial understanding in indoor videos. Built from ScanNet++ and ScanNet200, PinpointQA comprises 1,024 scenes and 10,094 QA pairs organized into four progressively challenging tasks: Target Presence Verification (TPV), Nearest Reference Identification (NRI), Fine-Grained Spatial Description (FSD), and Structured Spatial Prediction (SSP). The dataset is built from intermediate spatial representations, with QA pairs generated automatically and further refined through quality control. Experiments on representative MLLMs reveal a consistent capability gap along the progressive chain, with SSP remaining particularly difficult. Supervised fine-tuning on PinpointQA yields substantial gains, especially on the harder tasks, demonstrating that PinpointQA serves as both a diagnostic benchmark and an effective training dataset. The dataset and project page are available at https://rainchowz.github.io/PinpointQA.

Inference-time scaling for LLM reasoning has focused on three axes: chain depth, sample breadth, and learned step-scorers (PRMs). We introduce a fourth axis, granularity of external verbal supervision, via Verbal Process Supervision (VPS), a training-free framework that uses structured natural-language critique from a stronger supervisor to guide an iterative generate-critique-refine loop up to a round budget R. Across GPQA Diamond, AIME 2025, and LiveCodeBench V6 (covering both closed and open models), VPS yields three key results. First, on GPQA Diamond, GPT-5.4 (High) | GPT-5.4 (Low) reaches 94.9% at R=4, surpassing the 94.1% state of the art without gradient updates. Second, on AIME 2025, VPS enables strong weak-actor rescue, boosting scores from 11.7-26.7% to 63.3-90.0% (up to +63.3 points). Third, at matched compute, VPS outperforms Reflexion by +8.5 to +12.1 points and Self-Consistency@5 by +5.0 pp (GPQA) and +8.3 pp (LiveCodeBench), isolating critique granularity as the key driver. Performance scales with the supervisor-actor capability gap (Pearson r=0.90) and degrades when errors are not linguistically expressible (e.g., code synthesis), motivating hybrid verbal-executable methods. These results establish critique granularity as a new axis of inference-time scaling.

Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of tools such as notebooks, IDEs, terminals, browsers, and databases within real operating environments. Yet existing benchmarks lack real-computer interaction and do not evaluate whether agents can execute complete end-to-end data-science workflows in realistic computing environments, failing to capture the multi-stage, multi-tool nature of data-science practice. We introduce DSAgentBench, the first benchmark to evaluate whether agents can automate full data-science workflows inside real computer environments. DSAgentBench contains 275 diverse tasks covering the entire data-science life-cycle, reflecting the complexity and tool coordination required in practice. Each task requires grounding decisions in intermediate outputs and coordinated tool use, and includes a deterministic evaluator that verifies analytical correctness, visual outputs, and model performance rather than code-only execution. Our extensive experiments with 15 closed- and open-source models show that even the strongest agent, Claude-4.6-Sonnet, achieves only 56.70% task success, while all open-source agents remain below 1%, frequently failing at tool orchestration, OS grounding, and multi-step reasoning. These results reveal a substantial capability gap between current agentic systems and real data-science workflows, positioning DSAgentBench as a foundation for developing grounded, verifiable, autonomous data-science agents. We release DSAgentBench at https://github.com/vis-nlp/DSAgentBench.

Large language models (LLMs) have been widely adopted for clinical question answering (QA). Current systems can attach citations to their answers, but these often point to broad texts, leaving time-pressed clinicians unable to verify them efficiently. An alternative is to ensure that responses are verifiable by construction: providing fine-grained verbatim quotes from reference material that substantiate claims, so users can verify an answer without opening other documents. In this paper, we evaluate the ability of current models to perform this task end-to-end: from providing citations for every factual claim, to producing verbatim quotes, to ensuring that those quotes fully substantiate the claims. To do so, we build a standardized harness over four clinical practice guidelines and evaluate twelve LLMs on 222 synthetic clinical questions, measuring each of these stages separately. We find that most models can attach verbatim quotes to over 90% of their claims from prompting alone, apart from some lightweight models such as claude-haiku-4.5. Yet these quotes often fail to substantiate every detail of the claims they accompany. For instance, claude-opus-5 produces verbatim quotes for 98.0% of its claims, but fully substantiates only 37.1%. Our work provides insights into the current capability gap of LLMs in building verifiable clinical QA systems, along with artifacts for future research.

Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing users to communicate through speech and vision rather than carefully composed text prompts. However, existing benchmarks of interactive capabilities still focus primarily on response quality, leaving a more fundamental question underexplored: can a model correctly infer the user's underlying demand from complex multimodal interaction? Real-world user demands are often underspecified in speech and must be inferred from multimodal cues and dialogue history. This inference is further complicated by ambiguous or disfluent expression and noisy acoustic environments. Conversely, request-like speech may not constitute a demand to the assistant, leading to false triggers. We establish Omni Demand Understanding (ODU) as a distinct multimodal contextual inference problem: given an interaction stream, a model must detect whether a user demand is present and infer intent from multimodal and conversational context. ODU evaluates this capability along five dimensions, covering both single-turn and multi-turn interactions. We construct ODU-Bench using a challenge-driven taxonomy, taxonomy-guided agentic video generation, and human-recorded interactions, followed by media-grounded annotation and human verification. We evaluate 14 native MLLMs. Even the strongest, Gemini 3.1 Pro, recovers only 44.7% of key information that must be inferred from visual, acoustic, or conversational context. Moreover, 11 of the 14 models exhibit false-trigger rates above 50% on non-demand scenarios. These results reveal a systematic capability gap in current MLLMs' ability to infer contextual user demands. We hope ODU can establish the evaluation of a previously underexplored yet essential capability in multimodal interaction: correctly understanding user demands before generating an appropriate response.

Despite the rapid advance of Multimodal Large Language Models (MLLMs) in high-level video understanding, a fundamental bottleneck remains: these models collapse complex human motion into coarse semantic labels. Existing benchmarks mostly focus on scene-centric events or local joint articulations, failing to probe global human motion in space over time (trajectory and orientation changes). We introduce HumanMoveVQA, the first comprehensive benchmark designed to evaluate global trajectory and orientation reasoning from an exocentric perspective. Our benchmark utilizes a first-frame anchored world coordinate system, preserving translation and rotation relative to a fixed starting point. We propose a scalable, multi-stage pipeline that lifts 2D video observations into world-consistent 3D motion tracks to generate over 10K structured question-answer pairs across seven reasoning categories, including motion aggregation, sequential ordering, and trajectory-level inference. Our extensive evaluation reveals a critical capability gap in state-of-the-art proprietary models on deep human motion understanding. However, we demonstrate that this is a learnable problem; by fine-tuning an open-source baseline with our targeted, world-consistent supervision, we achieve a significant improvement. HumanMoveVQA establishes a rigorous geometric foundation for developing next-generation, movement-aware video understanding models.

Charts are a primary medium for conveying quantitative and relational information, yet systematically evaluating chart parsing models remains difficult. Existing benchmarks focus on narrow chart types and leave diagrammatic structures such as flowcharts and mind maps largely unaddressed, while models produce outputs in incompatible formats, and datasets rarely include the printed or hand-drawn images encountered in practice. To address these issues, we introduce ChartArena, a comprehensive bilingual benchmark covering eight chart families spanning both numeric charts and diagrammatic structures, each evaluated across three visual scenarios: digital renderings, printed photos, and hand-drawn photos. The dataset is built via a human-agent collaborative annotation pipeline with multi-stage human verification to ensure annotation reliability. To enable fair cross-model comparison, we further design a format-agnostic evaluation protocol that maps heterogeneous outputs into two canonical semantic spaces, a normalized triple view and a directed graph view, and scores them with structure-aware metrics. Through extensive evaluation of 26 leading MLLMs, we observe three consistent findings: (i) frontier proprietary models such as Gemini 3.1 Pro lead overall, yet the strongest open-source systems are rapidly closing the gap; (ii) document parsing models handle numeric charts reasonably but fall sharply behind on diagrammatic structures; and (iii) expert chart parsers remain limited to narrow chart families. Across all models, radar charts and hand-drawn scenarios stay especially challenging. These findings show that ChartArena exposes clear capability gaps and provides a unified foundation for future progress. ChartArena is publicly available at https://github.com/pspdada/ChartArena.

We study how runtime enforcement against unsafe actions affects end-to-end task performance in multi-step tool using large language model (LLM) agents. Using tau-bench across Airline and Retail domains, we compare baseline Tool-Calling, planning-integrated (TRIAD), and policy-mediated (TRIAD-SAFETY) architectures with GPT-OSS-20B and GLM-4-9B. We identify model dependent interaction horizons (15 to 30 turns) and decompose outcomes into overall success rate (SR), safe success rate (SSR), and unsafe success rate (USR). Our results reveal a persistent Safety Capability Gap. While safety mediation can intercept up to 94 percent of non-compliant actions, it rarely translates into strictly safe goal attainment (SSR below 5 percent in most settings). We find that high unsafe success rates are primarily driven by Integrity Leaks, where models hallucinate user identifiers to bypass mandatory authentication. Recovery rates following blocked actions are consistently low, ranging from 21 percent for GPT-OSS-20B in simpler procedural tasks to near zero in complex Retail scenarios. These results demonstrate that runtime enforcement imposes a significant verifier tax on conversational length and compute cost without guaranteeing safe completion, highlighting the critical need for agents capable of grounded identity verification and post-intervention reasoning.

Recursive self-improvement requires turning evidence of model failures into better models. Data-centric post-training research entails diagnosing capability gaps, designing and validating training-data strategies, and learning from checkpoint feedback. Can LLM agents automate this loop? Existing benchmarks entangle research decisions with optimization, serving, evaluation, and systems implementation, obscuring agents' research capability. We introduce RSIBench-Data, a controlled benchmark of LLM agents as data-centric researchers with a fixed post-training stack. Agents iteratively revise training-data strategies for a fixed target model; training and serving use Tinker-backed services, official evaluation runs through Harbor and E2B sandboxes, and budgets are fixed across agents. We evaluate four frontier agents on six benchmarks across software engineering, terminal use, scientific question answering, and mathematics. Agents demonstrate core data-centric research capabilities: in 58.33\% of settings, they improve upon the first valid attempt by refining strategies from feedback. However, improvement is inconsistent. Among searches continuing after the best observed score, 78.26\% end with a lower-scoring final attempt, while the rest only recover the same peak. A strong candidate may therefore appear early or midway through a run even as later revisions fail. Trajectory analysis identifies four patterns in stronger runs: accurate hypotheses, validation-grounded supervision, behavior-aligned data, and preservation of strong checkpoints. These findings suggest that current agents can make useful data-centric discoveries but cannot yet translate feedback into consistent improvements. RSIBench-Data provides a measurable, auditable testbed for the research capabilities required for recursive self-improvement. We open-source our code at https://github.com/evolvent-ai/RSIBench-Data.

When a professional web developer's code fails a test, they do not simply re-read the stack trace. They open the application in a browser, click buttons, inspect computed styles, and run diagnostic commands to understand what went wrong. Existing feedback mechanisms for coding agents rely on screenshots, LLM-as-a-judge scoring, or natural-language corrections, but few interact with the live application the way a developer would. We introduce WatchPoint, a simulated-user system that mimics real developer behavior by generating and executing diagnostic scripts against the running application, producing structured observations that guide the coding model's retry. Unlike prior approaches that target single-file edits or evaluate using non-executable metrics, we operate on Web-Bench, a benchmark of 50 multi-file web projects comprising 1,000 sequentially dependent tasks, verified by deterministic end-to-end tests. WatchPoint recovers 57.6% of the tasks it diagnoses, and a controlled user study confirms the simulation's realism: human testers achieve a comparable recovery rate (54.5%), providing evidence that automated diagnostic scripts can substitute for interactive human testing on sequential web development tasks. We further identify a pattern of capability gaps that governs when simulated-user feedback is helpful and when it should be withheld.

The growing use of language models for forecasting motivates a broader evaluation of their world-model capabilities. Such evaluation must go beyond predictive accuracy to assess hidden-state inference and intervention prediction. Real-world forecasting benchmarks offer limited access to hidden-state ground truth and controlled experiments. We introduce CivWorldBench, a benchmark built on a multi-agent strategy game engine with recorded internal states, controlled observations, and paired intervention rollouts. Its 1,900 decision points from 475 worlds support three task levels: association forecasting, belief inference, and intervention prediction. Reference predictors support attributable evaluation of capability gaps, with an expert harness and empirical ceiling estimates contextualizing scores. Stored trajectories make intermediate predictions verifiable, while agent-play experiments test whether world-model capabilities support decision-making. The main panel comprises eleven frontier language models. Composite benchmark scores correlate with real-world forecasting leaderboards on matched model panels, more closely than with a general-capability index, supporting its use as a proxy for real-world forecasting capability. Strong association forecasts do not consistently extend to belief inference or intervention prediction, and effect magnitudes remain poorly calibrated despite informative direction predictions. Process verification reveals errors missed by final-answer evaluation, and structured reasoning improves intervention prediction for the strongest model in the process study. Agent-play experiments identify useful assisted plans and motivate evaluating decision-relevant capabilities beyond association forecasting. These findings identify hidden-state inference, intermediate-state prediction, and effect calibration as priorities for world-model training.

Vision Language Models (VLMs) have undergone a rapid evolution, giving rise to significant advancements in the realm of multimodal understanding tasks. However, the majority of these models are trained and evaluated on English-centric datasets, leaving a gap in the development and evaluation of VLMs for other languages, such as Japanese. This gap can be attributed to the lack of methodologies for constructing VLMs and the absence of benchmarks to accurately measure their performance. To address this issue, we introduce a novel benchmark, Japanese Heron-Bench, for evaluating Japanese capabilities of VLMs. The Japanese Heron-Bench consists of a variety of imagequestion answer pairs tailored to the Japanese context. Additionally, we present a baseline Japanese VLM that has been trained with Japanese visual instruction tuning datasets. Our Heron-Bench reveals the strengths and limitations of the proposed VLM across various ability dimensions. Furthermore, we clarify the capability gap between strong closed models like GPT-4V and the baseline model, providing valuable insights for future research in this domain. We release the benchmark dataset and training code to facilitate further developments in Japanese VLM research.

Programming assistants powered by large language models have transformed software development, yet most benchmarks focus narrowly on code generation tasks. Recent efforts like InfiBench and StackEval attempt to address this gap using Stack Overflow data but remain limited to single-turn interactions in isolated contexts, require significant manual curation, and fail to represent complete project environments. We introduce CodeAssistBench (CAB), the first benchmark framework for evaluating multi-turn programming assistance in realistic settings that address real-world questions about actual codebases. Unlike existing programming Q&A benchmarks, CAB automatically generates scalable datasets from question-related GitHub issues using configurable parameters (e.g., repository creation date, star count, programming languages), and includes automatic containerization of codebases for evaluation. It then evaluates models through simulated users in these containerized environments with full codebase access. Using this framework, we constructed a test set of 3,286 real-world programming questions across 231 repositories, spanning seven programming languages and diverse problem domains. Our evaluation of leading LLMs reveals a substantial capability gap: while models perform well on Stack Overflow questions with success rates of 70-83%, they resolve only up to 16.49% of CAB's recent issues. This discrepancy highlights the challenges of providing assistance in complex, project-specific contexts versus answering standalone questions.

Existing benchmarks for AI coding agents focus on isolated, single-issue tasks such as fixing a bug or implementing a small feature. However, real-world software engineering is fundamentally a long-horizon endeavor: developers must interpret high-level requirements, plan coordinated changes across many files, and evolve codebases over multiple iterations while preserving existing functionality. We introduce SWE-EVO, a benchmark that evaluates agents on this long-horizon software evolution challenge. Constructed from release notes and version histories of seven mature open-source Python projects, Tool comprises 48 evolution tasks that require agents to implement multi-step modifications spanning an average of 21 files, validated against comprehensive test suites averaging 874 tests per instance. Experiments with state-of-the-art models reveal a striking capability gap: even GPT-5 with OpenHands achieves only a 21 percent resolution rate on Tool, compared to 65 percent on the single-issue SWE-Bench Verified. This demonstrates that current agents struggle with sustained, multi-file reasoning. We also propose Fix Rate, a fine-grained metric that captures partial progress toward solving these complex, long-horizon tasks.

Composed Image Retrieval (CIR) is a pivotal and complex task in multimodal understanding. Current CIR benchmarks typically feature limited query categories and fail to capture the diverse requirements of real-world scenarios. To bridge this evaluation gap, we leverage image editing to achieve precise control over modification types and content, enabling a pipeline for synthesizing queries across a broad spectrum of categories. Using this pipeline, we construct EDIR, a novel fine-grained CIR benchmark. EDIR encompasses 5,000 high-quality queries structured across five main categories and fifteen subcategories. Our comprehensive evaluation of 13 multimodal embedding models reveals a significant capability gap; even state-of-the-art models (e.g., RzenEmbed and GME) struggle to perform consistently across all subcategories, highlighting the rigorous nature of our benchmark. Through comparative analysis, we further uncover inherent limitations in existing benchmarks, such as modality biases and insufficient categorical coverage. Furthermore, an in-domain training experiment demonstrates the feasibility of our benchmark. This experiment clarifies the task challenges by distinguishing between categories that are solvable with targeted data and those that expose intrinsic limitations of current model architectures.

Autonomous agents have made rapid progress in general-purpose computer use, but reliable automation of professional industrial engineering remains out of reach, as engineering workflows demand reasoning over geometric and physical constraints and dependencies preserved across software and design stages. We present EngiWorld, the first benchmark structured around the complete design loop: 1,301 expert-curated tasks spanning 6 engineering domains (CAD, CAE, CAM, BIM, EDA, and 3D visualization) and 26 professional software platforms, with both GUI and CLI interfaces and 6 task types ranging from software-selection to open-ended tasks. We further introduce an artifact-centric evaluation methodology built on a unified domain-verifier suite, which programmatically checks the geometric validity, physical feasibility, and rule compliance of final and intermediate artifacts, and scores quantitative design tasks continuously by specification attainment rather than binary success. Evaluation of seven frontier models reveals a substantial capability gap: the strongest model achieves an EngiScore of only 44.3, and just 3.6% of multi-software attempts succeed. EngiWorld provides the first rigorous foundation for measuring progress toward agents that operate professional engineering software end to end.

Sparse attention can effectively mitigate the significant memory and throughput demands of Large Language Models (LLMs) in long contexts. Existing methods typically employ a uniform sparse attention mask, applying the same sparse pattern across different attention heads and input lengths. However, this uniform approach fails to capture the diverse attention patterns inherent in LLMs, ignoring their distinct accuracy-latency trade-offs. To address this challenge, we propose the Mixture of Attention (MoA), which automatically tailors distinct sparse attention configurations to different heads and layers. MoA constructs and navigates a search space of various attention patterns and their scaling rules relative to input sequence lengths. It profiles the model, evaluates potential configurations, and pinpoints the optimal sparse attention compression plan. MoA adapts to varying input sizes, revealing that some attention heads expand their focus to accommodate longer sequences, while other heads consistently concentrate on fixed-length local contexts. Experiments show that MoA increases the effective context length by 3.9times with the same average attention span, boosting retrieval accuracy by 1.5-7.1times over the uniform-attention baseline across Vicuna-7B, Vicuna-13B, and Llama3-8B models. Moreover, MoA narrows the capability gaps between sparse and dense models, reducing the maximum relative performance drop from 9%-36% to within 5% across two long-context understanding benchmarks. MoA achieves a 1.2-1.4times GPU memory reduction and boosts decode throughput by 5.5-6.7 times for 7B and 13B dense models on a single GPU, with minimal impact on performance.

As Large Language Models (LLMs) are increasingly deployed as autonomous agents, they face a critical scalability bottleneck known as the "Generalization-Specialization Dilemma." Monolithic agents equipped with extensive toolkits suffer from context pollution and attention decay, leading to hallucinations. Conversely, static multi-agent swarms introduce significant latency and resource overhead. This paper introduces a Self-Evolving Concierge System, a novel architecture utilizing a Dynamic Mixture of Experts (DMoE) approach. Unlike recent self-improving agents that rewrite their own codebase, our system preserves stability by dynamically restructuring its runtime environment: "hiring" specialized sub-agents based on real-time conversation analysis. We introduce an asynchronous "Meta-Cognition Engine" that detects capability gaps, a Least Recently Used (LRU) eviction policy for resource constraints, and a novel "Surgical History Pruning" mechanism to mitigate refusal bias. Experimental results demonstrate that this architecture maintains high task success rates while minimizing token consumption compared to static agent swarms.

Financial tasks are pivotal to global economic stability; however, their execution faces challenges including labor intensive processes, low error tolerance, data fragmentation, and tool limitations. Although large language models (LLMs) have succeeded in various natural language processing tasks and have shown potential in automating workflows through reasoning and contextual understanding, current benchmarks for evaluating LLMs in finance lack sufficient domain-specific data, have simplistic task design, and incomplete evaluation frameworks. To address these gaps, this article presents FinMaster, a comprehensive financial benchmark designed to systematically assess the capabilities of LLM in financial literacy, accounting, auditing, and consulting. Specifically, FinMaster comprises three main modules: i) FinSim, which builds simulators that generate synthetic, privacy-compliant financial data for companies to replicate market dynamics; ii) FinSuite, which provides tasks in core financial domains, spanning 183 tasks of various types and difficulty levels; and iii) FinEval, which develops a unified interface for evaluation. Extensive experiments over state-of-the-art LLMs reveal critical capability gaps in financial reasoning, with accuracy dropping from over 90% on basic tasks to merely 40% on complex scenarios requiring multi-step reasoning. This degradation exhibits the propagation of computational errors, where single-metric calculations initially demonstrating 58% accuracy decreased to 37% in multimetric scenarios. To the best of our knowledge, FinMaster is the first benchmark that covers full-pipeline financial workflows with challenging tasks. We hope that FinMaster can bridge the gap between research and industry practitioners, driving the adoption of LLMs in real-world financial practices to enhance efficiency and accuracy.

Agent skills extend LLM agents with reusable procedures, tools, and domain-specific workflows, but their safety depends on resolving dependencies among interacting instructions. We introduce SkillLogic, a framework for analyzing logical relations in skill files and constructing executable tests from them. Our taxonomy covers eight relation types, including preconditions that gate valid actions, constraints that limit how allowed actions may be performed, and fallbacks that specify recovery behavior after failure. Using SkillLogic, we scan over 5000 public skills and find that 70% contain at least one logical relation. We then construct SLBench, an 86-case executable benchmark from high-confidence, high-impact, and locally testable relations. Evaluating Codex and Claude Code across six LLM backbones shows unsafe rates up to 70%, with violations leading to privacy leaks, unsafe configuration changes, and incomplete cleanup. The human audit attributes failures to both agent capability gaps and low-salience skill text. We further show that SLGuard, a lightweight inference-time scaffold, reduces violations by 63% on targeted cases. Our results establish logical-relation following as a distinct reliability challenge for skill-guided agents.

Assessing cybersecurity vulnerability awareness in coding agents requires evaluations that reveal capability gaps and remain informative as models evolve. Static benchmarks offer fixed coverage and difficulty, while scarce vulnerable repositories and costly expert authoring limit their renewal at scale. We introduce SecProbe, a framework for adaptive evaluation that combines Item Response Theory (IRT) with on-demand synthesis of repository-scale vulnerability-repair tasks. From observed performance, SecProbe estimates agent ability and identifies where additional evidence is most informative, selecting existing tasks or synthesizing new ones accordingly. As one use case, we construct 353 tasks spanning six programming languages and 151 CWE types and evaluate nine frontier models with two agent harnesses. Success rates peak at 28.33\%, highlighting substantial gaps in vulnerability recognition and repair. Compared with random and one-shot baselines, SecProbe achieves comparable agent ability estimates while requiring agents to solve up to 29.5\% fewer tasks. These results support adaptive evaluation as an efficient and discriminative approach to assessing cybersecurity vulnerability awareness.

Time series agents answer analytical questions by calling external tools, and which tools they carry is decided by people before the agent runs. However, we identify two failures in this setup. Human-Agent Tool Misalignment: a library of 21 expert-curated tools helps on some tasks and hurts on others, dropping anomaly accuracy under every backbone we test. Silent Harm: one round of generic self-revision changes 147 answers and breaks 56 of them, while the final score moves by less than a point. Both follow from the same gap: whether a tool helps is decided question by question at runtime, while tools are supplied in advance and judged by a single average. To address this, we propose TimeEvo, which clusters an agent's diagnosed failures into capability gaps, plans a measurement for each, synthesizes evidence-only tools that fill them, and admits the candidate library only through a paired admission gate. Experiments on ten time series QA tasks and three backbones show that TimeEvo, starting from an empty library, improves accuracy on every task and every backbone, and that a library grown on a cheap model still gains when it is installed into stronger ones. Code is available at https://github.com/Muyiiiii/TimeEvo.

Context compression improves long-context efficiency but may introduce faithfulness issues through an information bottleneck. Existing evaluations rely on QA metrics, but a reader can still answer correctly from an unfaithful compression, so these metrics underestimate such loss. To bridge this gap, we introduce KEEP-Bench, a diagnostic benchmark that directly assesses compression faithfulness with 4,102 cases across three challenging settings that require keeping evidence for plausible reference resolutions, explicit qualifiers, and minority perspectives. Experiments show that even with tailored prompting, the strongest models remain unreliable: despite context windows exceeding 100K tokens and inputs averaging only 3.1K tokens, the best open-weight model (31B) preserves all required evidence in only 66.8% of cases, and the best proprietary model in only 61.6%. Performance also varies sharply across evidence structures, so conclusions from limited structures may be biased. We further introduce a metric, Evidence Preservation Return (EPR), to relate evidence recall to inference FLOPs, and find that it peaks at moderate scales (4B-8B), where recall remains low. Additional output budget mainly benefits already strong models and widens capability gaps, yet the stronger preservation of these models comes at a steep computational cost. These findings highlight the importance for future work to investigate compressors with strong information preservation under a small computation budget, rather than relying on a large output budget or model scaling.

Current evaluation paradigms for large language models (LLMs) represent a critical blind spot in AI research--relying on opaque numerical metrics that conceal fundamental limitations in spatial reasoning while providing no intuitive understanding of model capabilities. This deficiency creates a dangerous disconnect between reported performance and practical abilities, particularly for applications requiring physical world understanding. We introduce LTD-Bench, a breakthrough benchmark that transforms LLM evaluation from abstract scores to directly observable visual outputs by requiring models to generate drawings through dot matrices or executable code. This approach makes spatial reasoning limitations immediately apparent even to non-experts, bridging the fundamental gap between statistical performance and intuitive assessment. LTD-Bench implements a comprehensive methodology with complementary generation tasks (testing spatial imagination) and recognition tasks (assessing spatial perception) across three progressively challenging difficulty levels, methodically evaluating both directions of the critical language-spatial mapping. Our extensive experiments with state-of-the-art models expose an alarming capability gap: even LLMs achieving impressive results on traditional benchmarks demonstrate profound deficiencies in establishing bidirectional mappings between language and spatial concept--a fundamental limitation that undermines their potential as genuine world models. Furthermore, LTD-Bench's visual outputs enable powerful diagnostic analysis, offering a potential approach to investigate model similarity.

The deployment of coding agents in privacy-sensitive and resource-constrained environments drives the demand for capable open-weight Small Language Models (SLMs). However, they suffer from a fundamental capability gap: unlike frontier large models, they lack the inference-time strong generalization to work with complicated, unfamiliar codebases. We identify that the prevailing Task-Centric Learning (TCL) paradigm, which scales exposure across disparate repositories, fails to address this limitation. In response, we propose Repository-Centric Learning (RCL), a paradigm shift that prioritizes vertical repository depth over horizontal task breadth, suggesting SLMs must internalize the "physics" of a target software environment through parametric knowledge acquisition, rather than attempting to recover it via costly inference-time search. Following this new paradigm, we design a four-unit Repository-Centric Experience, transforming static codebases into interactive learning signals, to train SWE-Spot-4B, a family of highly compact models built as repo-specialized experts that breaks established scaling trends, outperforming open-weight models up to larger (e.g., CWM by Meta, Qwen3-Coder-30B) and surpassing/matching efficiency-focused commercial models (e.g., GPT-4.1-mini, GPT-5-nano) across multiple SWE tasks. Further analysis reveals that RCL yields higher training sample efficiency and lower inference costs, emphasizing that for building efficient intelligence, repository mastery is a distinct and necessary dimension that complements general coding capability.

Large language models achieve near-ceiling performance on code generation benchmarks, yet these results increasingly reflect memorization rather than genuine reasoning. We introduce EsoLang-Bench, a benchmark using five esoteric programming languages (Brainfuck, Befunge-98, Whitespace, Unlambda, and Shakespeare) that lack benchmark gaming incentives due to their economic irrationality for pre-training. These languages require the same computational primitives as mainstream programming but have 1,000-100,000x fewer public repositories than Python (based on GitHub search counts). We evaluate five frontier models across five prompting strategies and find a dramatic capability gap: models achieving 85-95% on standard benchmarks score only 0-11% on equivalent esoteric tasks, with 0% accuracy beyond the Easy tier. Few-shot learning and self-reflection fail to improve performance, suggesting these techniques exploit training priors rather than enabling genuine learning. EsoLang-Bench provides the first benchmark designed to mimic human learning by acquiring new languages through documentation, interpreter feedback, and iterative experimentation, measuring transferable reasoning skills resistant to data contamination.

Large language models (LLMs) have enabled agentic systems that can reason, plan, and act across complex tasks, but it remains unclear whether they can allocate resources effectively under uncertainty. Unlike short-horizon reactive decisions, allocation requires committing scarce resources over time while balancing competing objectives and preserving flexibility for future needs. We introduce EnterpriseArena, the first benchmark for evaluating agents on long-horizon enterprise resource allocation. It instantiates CFO-style decision-making in a 132-month enterprise simulator combining firm-level financial data, anonymized business documents, macroeconomic and industry signals, and expert-validated operating rules. The environment is partially observable and reveals the state only through budgeted organizational tools, forcing agents to trade off information acquisition against conserving scarce resources. Experiments on eleven advanced LLMs show that this setting remains highly challenging: only 16% of runs survive the full horizon, and larger models do not reliably outperform smaller ones. These results identify long-horizon resource allocation under uncertainty as a distinct capability gap for current LLM agents.

Recently, unified multimodal models (UMMs) have made remarkable progress in integrating visual understanding and generation, demonstrating strong potential for complex text-to-image (T2I) tasks. Despite their theoretical promise, a persistent capability gap exists: UMMs typically exhibit superior visual understanding but comparatively weaker generative capabilities. This discrepancy arises largely from the intrinsic decoupling between the understanding and generation processes. While a UMM can accurately interpret fine-grained visual details, it often struggles to produce semantically coherent images from complex textual prompts. To address this challenge, we explore UMMs' internal understanding capability to enhance generation quality. We propose a token-level intrinsic text-image alignment reward mechanism, GvU, enabling the UMM to act simultaneously as teacher and student: it evaluates its own outputs using the understanding branch to guide the generations accordingly. Building upon this, we design a self-supervised reinforcement learning framework, allowing UMMs to iteratively improve their generation quality through understanding-based intrinsic reward signals--without reliance on external supervision. Experimental results show that our method substantially boosts UMMs' generation, which in turn strengthens their fine-grained visual understanding, narrowing the capability gap between UMMs' visual understanding and generation.

Generative image editing models struggle with structured statistical charts when data modifications require geometric synchronization. We formalize this task as Visuo-Logical Cascading Editing (VLCE). However, existing methods remain confined to localized text substitutions and struggle with dependency-aware cascading updates. To systematically evaluate this capability, we introduce ChartSync, an expert-validated benchmark constructed via a programmatic rendering pipeline that guarantees deterministic visuo-logical coupling for the ground truth. ChartSync comprises 870 triplets across 9 chart categories and 4 task types, including 235 geometry-coupled VLCE instances that specifically test cascading text-to-geometry synchronization. We further evaluate these instances via a two-tier framework combining objective visual metrics with a vision-language model judge paradigm to assess low-level fidelity alongside multimodal comprehension and reasoning. Evaluating 14 image editing models and one code-mediated pipeline reveals a nuanced capability gap: most open-source models suffer severe drops in geometric synchronization, while only two frontier proprietary models show emerging VLCE capability, with their residual errors mainly involving semantic isolation and background corruption. Our detailed error analysis deconstructs these failure paradigms to identify core meta-abilities for guiding future multimodal architectures. The ChartSync dataset and code are publicly released at https://github.com/kaka-yjk/ChartSyncCodebase.

We present Apriel-1.5-15B-Thinker, a 15-billion parameter open-weights multimodal reasoning model that achieves frontier-level performance through training design rather than sheer scale. Starting from Pixtral-12B, we apply a progressive three-stage methodology: (1) depth upscaling to expand reasoning capacity without pretraining from scratch, (2) staged continual pre-training that first develops foundational text and vision understanding, then enhances visual reasoning through targeted synthetic data generation addressing spatial structure, compositional understanding, and fine-grained perception, and (3) high-quality text-only supervised fine-tuning on curated instruction-response pairs with explicit reasoning traces spanning mathematics, coding, science, and tool use. Notably, our model achieves competitive results without reinforcement learning or preference optimization, isolating the contribution of our data-centric continual pre-training approach. On the Artificial Analysis Intelligence Index, Apriel-1.5-15B-Thinker attains a score of 52, matching DeepSeek-R1-0528 despite requiring significantly fewer computational resources. Across ten image benchmarks, its performance is on average within five points of Gemini-2.5-Flash and Claude Sonnet-3.7, a key achievement for a model operating within single-GPU deployment constraints. Our results demonstrate that thoughtful mid-training 2 design can close substantial capability gaps without massive scale, making frontier-level multimodal reasoning accessible to organizations with limited infrastructure. We release the model checkpoint, all training recipes, and evaluation protocols under the MIT license to to advance open-source research.

Current mobile GUI agent benchmarks systematically fail to assess memory capabilities, with only 5.2-11.8% memory-related tasks and no cross-session learning evaluation. We introduce MemGUI-Bench, a comprehensive memory-centric benchmark with pass@k and staged LLM-as-judge evaluation. Our contributions include: (1) a systematic memory taxonomy analyzing 11 agents across 5 architectures; (2) 128 tasks across 26 applications where 89.8% challenge memory through cross-temporal and cross-spatial retention; (3) MemGUI-Eval, an automated pipeline with Progressive Scrutiny and 7 hierarchical metrics; and (4) RQ-driven assessment of 11 state-of-the-art agents. Our experiments reveal significant memory deficits across all evaluated systems, identify 5 distinct failure modes, and synthesize 5 actionable design implications. All resources including code, benchmark, and evaluation results will be \textit{fully open-sourced and continuously maintained} at https://lgy0404.github.io/MemGUI-Bench/.

KV-cache eviction caps the memory cost of long reasoning traces but is inherently lossy because the model decodes from a partial view of its history. Under aggressive budgets, this not only lowers accuracy but can also cause runaway degeneration, where the model produces incoherent or repetitive tokens until reaching the length limit. We characterize much of this loss as an information gapf caused by missing context, rather than a capability gap caused by limited model capacity. An evicted 7B model and a full-context 1.5B model make complementary errors, and an oracle choice between their answers recovers 79% of the accuracy gap to the full-KV 7B model. Based on this observation, we propose KV-Rescue, a training-free inference framework that bridges the information gap introduced by KV eviction using a lightweight full-context helper. KV-Rescue interleaves reasoning steps from the two models into a shared trajectory. An online detector uses entropy and compressibility to terminate the generation of incoherent or repetitive base-model candidates early. Across five math benchmarks with Qwen2.5-Math 7B and 72B, KV-Rescue recovers an average of 87% of the accuracy lost to eviction at eviction budget B=64. A decode-cost analysis further shows that preventing runaway degeneration cuts base-model token generation by 43% on average.

On-policy distillation (OPD) improves reasoning models by learning the token-level discrepancy between a stronger teacher and an on-policy student. However, this discrepancy does not purely reflect the capability gap between the teacher and the student: it also contains deviations arising from the teacher itself, which are consequently mixed into the observed teacher--student discrepancy and indiscriminately learned by standard OPD during training. This issue is further exacerbated by privileged OPD, where privileged information induces larger teacher-side likelihood shifts, thereby encouraging the student to learn more of the teacher's own deviation. We introduce Calibrated On-Policy Distillation (Cal-OPD), which estimates the teacher's self-deviation region through positive and negative privileged interventions and calibrates the original teacher--student discrepancy by retaining only the component that lies beyond this region. Experiments on mathematical reasoning benchmarks show that, while retaining only about 52--65\% of the original teacher--student discrepancy as the optimization signal, Cal-OPD consistently outperforms standard OPD and its variants across model scales.

Vericoding refers to the generation of formally verified code from rigorous specifications. Recent AI models show promise in vericoding, but a unified methodology for cross-paradigm evaluation is lacking. Existing benchmarks test only individual languages/tools (e.g., Dafny, Verus, and Lean) and each covers very different tasks, so the performance numbers are not directly comparable. We address this gap with AlgoVeri, a benchmark that evaluates vericoding of 77 classical algorithms in Dafny, Verus, and Lean. By enforcing identical functional contracts, AlgoVeri reveals critical capability gaps in verification systems. While frontier models achieve tractable success in Dafny (40.3% for Gemini-3 Flash), where high-level abstractions and SMT automation simplify the workflow, performance collapses under the systems-level memory constraints of Verus (24.7%) and the explicit proof construction required by Lean (7.8%). Beyond aggregate metrics, we uncover a sharp divergence in test-time compute dynamics: Gemini-3 effectively utilizes iterative repair to boost performance (e.g., tripling pass rates in Dafny), whereas GPT-OSS saturates early. Finally, our error analysis shows that language design affects the refinement trajectory: while Dafny allows models to focus on logical correctness, Verus and Lean trap models in persistent syntactic and semantic barriers. All data and evaluation code can be found at https://github.com/haoyuzhao123/algoveri.

Large Language Models (LLMs) have marked a significant advancement in the field of natural language processing, demonstrating exceptional capabilities in reasoning, tool usage, and memory. As their applications extend into multi-agent environments, a need has arisen for a comprehensive evaluation framework that captures their abilities in reasoning, planning, collaboration, and more. This work introduces a novel benchmarking framework specifically tailored to assess LLMs within multi-agent settings, providing quantitative metrics to evaluate their judgment, reasoning, deception, self-awareness, cooperation, coordination, and rationality. We utilize games such as Chameleon and Undercover, alongside game theory scenarios like Cost Sharing, Multi-player Prisoner's Dilemma, and Public Good, to create diverse testing environments. Our framework is fortified with the Probabilistic Graphical Modeling (PGM) method, enhancing the LLMs' capabilities in navigating complex social and cognitive dimensions. The benchmark evaluates seven multi-agent systems powered by different LLMs, quantitatively highlighting a significant capability gap over threefold between the strongest, GPT-4, and the weakest, Llama-2-70B. It also confirms that our PGM enhancement boosts the inherent abilities of all selected models by 50% on average. Our codes are released here https://github.com/cathyxl/MAgIC.

Class-Incremental Semantic Segmentation (CISS) requires continuous learning of newly introduced classes while retaining knowledge of past classes. By abstracting mainstream methods into two stages (visual feature extraction and prototype-feature matching), we identify a more fundamental challenge termed catastrophic semantic entanglement. This phenomenon involves Prototype-Feature Entanglement caused by semantic misalignment during the incremental process, and Background-Increment Entanglement due to dynamic data evolution. Existing techniques, which rely on visual feature learning without sufficient cues to distinguish targets, introduce significant noise and errors. To address these issues, we introduce a Language-inspired Bootstrapped Disentanglement framework (LBD). We leverage the prior class semantics of pre-trained visual-language models (e.g., CLIP) to guide the model in autonomously disentangling features through Language-guided Prototypical Disentanglement and Manifold Mutual Background Disentanglement. The former guides the disentangling of new prototypes by treating hand-crafted text features as topological templates, while the latter employs multiple learnable prototypes and mask-pooling-based supervision for background-incremental class disentanglement. By incorporating soft prompt tuning and encoder adaptation modifications, we further bridge the capability gap of CLIP between dense and sparse tasks, achieving state-of-the-art performance on both Pascal VOC and ADE20k, particularly in multi-step scenarios.

Small language models (SLMs; 1-12B params, sometimes up to 20B) are sufficient and often superior for agentic workloads where the objective is schema- and API-constrained accuracy rather than open-ended generation. We synthesize recent evidence across open and proprietary SLMs (Phi-4-Mini, Qwen-2.5-7B, Gemma-2-9B, Llama-3.2-1B/3B, Ministral-3B/8B, Apple on-device 3B, DeepSeek-R1-Distill) and connect it to modern evaluations (BFCL v3/v4, StableToolBench) and serving stacks (vLLM, SGLang, TensorRT-LLM) paired with guided decoding libraries (XGrammar, Outlines). We formalize SLM-default, LLM-fallback systems with uncertainty-aware routing and verifier cascades, and propose engineering metrics that reflect real production goals: cost per successful task (CPS), schema validity rate, executable call rate, p50/p95 latency, and energy per request. Guided decoding, strict JSON Schema outputs, and validator-first tool execution close much of the capability gap with larger models and often let SLMs match or surpass LLMs on tool use, function calling, and RAG at 10x-100x lower token cost with materially better latency and energy. We provide design patterns for agent stacks that prioritize SLMs: schema-first prompting, type-safe function registries, confidence scoring with verifier rollups, and lightweight adaptation via LoRA/QLoRA. We also delineate limits where fallback remains valuable (open-domain reasoning and some long-horizon planning). The result is a practical blueprint for building fast, inexpensive, and reliable agents that default to SLMs while preserving headroom with targeted LLM assistance. Keywords: small language models, agents, function calling, structured outputs, JSON Schema, guided decoding, LoRA/QLoRA, routing, energy efficiency, edge inference

The deployment of large language models (LLMs) in automated negotiation has set a high performance benchmark, but their computational cost and data privacy requirements render them unsuitable for many privacy-sensitive, on-device applications such as mobile assistants, embodied AI agents or private client interactions. While small language models (SLMs) offer a practical alternative, they suffer from a significant performance gap compared to LLMs in playing emotionally charged complex personas, especially for credit negotiation. This paper introduces EQ-Negotiator, a novel framework that bridges this capability gap using emotional personas. Its core is a reasoning system that integrates game theory with a Hidden Markov Model(HMM) to learn and track debtor emotional states online, without pre-training. This allows EQ-Negotiator to equip SLMs with the strategic intelligence to counter manipulation while de-escalating conflict and upholding ethical standards. Through extensive agent-to-agent simulations across diverse credit negotiation scenarios, including adversarial debtor strategies like cheating, threatening, and playing the victim, we show that a 7B parameter language model with EQ-Negotiator achieves better debt recovery and negotiation efficiency than baseline LLMs more than 10 times its size. This work advances persona modeling from descriptive character profiles to dynamic emotional architectures that operate within privacy constraints. Besides, this paper establishes that strategic emotional intelligence, not raw model scale, is the critical factor for success in automated negotiation, paving the way for effective, ethical, and privacy-preserving AI negotiators that can operate on the edge.

Computer Use Agents (CUAs) translate natural-language instructions into Graphical User Interface (GUI) actions such as clicks, keystrokes, and scrolls by relying on a Vision-Language Model (VLM) to interpret screenshots and predict grounded tool calls. However, grounding accuracy varies dramatically across VLMs, while current CUA systems typically route every action to a single fixed model regardless of difficulty. We propose Adaptive VLM Routing (AVR), a framework that inserts a lightweight semantic routing layer between the CUA orchestrator and a pool of VLMs. For each tool call, AVR estimates action difficulty from multimodal embeddings, probes a small VLM to measure confidence, and routes the action to the cheapest model whose predicted accuracy satisfies a target reliability threshold. For warm agents with memory of prior UI interactions, retrieved context further narrows the capability gap between small and large models, allowing many actions to be handled without escalation. We formalize routing as a cost--accuracy trade-off, derive a threshold-based policy for model selection, and evaluate AVR using ScreenSpot-Pro grounding data together with the OpenClaw agent routing benchmark. Across these settings, AVR projects inference cost reductions of up to 78\% while staying within 2 percentage points of an all-large-model baseline. When combined with the Visual Confused Deputy guardrail, AVR also escalates high-risk actions directly to the strongest available model, unifying efficiency and safety within a single routing framework. Materials are also provided Model, benchmark, and code: https://github.com/vllm-project/semantic-router.

The inherent complexity of video understanding makes it difficult to determine whether Video-LLM benchmark performance stems from visual perception, linguistic reasoning, or knowledge priors. While many benchmarks have emerged to assess high-level reasoning, shared criteria for evaluating video understanding remain largely overlooked. Instead of introducing yet another benchmark, we take a step back to re-examine the criteria for evaluating video understanding. In this work, we introduce Video-Oasis, a sustainable diagnostic suite for systematically auditing existing video understanding benchmarks. This audit reveals that 55\% of existing benchmark samples are solvable without visual input or temporal context. After filtering these shortcuts, the remaining video-native challenges expose a substantial capability gap: state-of-the-art models perform only marginally above random guessing. Building on these findings, we use the distilled challenges as a testbed to investigate which algorithmic design choices contribute to robust video understanding. We hope our work provides a practical foundation for constructing rigorous video benchmarks and evaluating future Video-LLMs. Code is available at https://github.com/sejong-rcv/Video-Oasis.

Audio-video generation is rapidly moving from prompt-driven synthesis toward multimodal conditioning, where text, images, audio, and video can jointly shape the generated output. This shift changes the nature of safety evaluation: harmful intent may no longer reside in any single input, but instead emerge from how otherwise benign or weakly harmful conditions interact across modalities and time. Existing safety benchmarks, however, remain largely prompt-centric or tied to fixed conditioning interfaces, leaving such compositional risks difficult to study systematically. To bridge this gap, we introduce Multi2AV-Safety, the first safety benchmark, to the best of our knowledge, to cover all 11 non-singleton T/I/A/V conditioning configurations for audio-video generation, comprising 11,024 attack instances. Evaluation on Multi2AV-Safety reveals systematic weaknesses in representative multimodal safety guards across attack mechanisms and harm-evidence structures. Our evaluation reveals two complementary failure modes: harmful semantics can emerge from the combination of individually benign inputs, while explicit harmful cues can become harder to detect when mixed with benign multimodal context. Together, these results identify compositional risk perception as a central capability gap in safeguarding multimodal-conditioned audio-video generation: current safety guards fail to reliably integrate safety evidence across modalities and time, even when all conditioning inputs are observable. The dataset will be publicly released in October 2026.

Evaluating agents by outcomes alone can obscure the capabilities that produce them. This problem is especially pronounced in evolving environments, where outcomes reflect a closed-loop interaction between agent behavior and changing external conditions. We introduce LiveMACEBench, a process-aware benchmark that uses live financial markets as a naturally evolving testbed for persistent LLM agents. Five frontier LLMs operate along continuous trajectories under matched Tool Use, Persistent Memory, Rule Following, and Multi-Agent Collaboration configurations. We evaluate them through both realized outcomes and mechanism-specific diagnostics derived from complete decision traces. Across 30 days of live evaluation, we find a pronounced outcome-capability gap: realized returns often diverge from capability-specific measurements, and similar outcomes can arise from markedly different patterns of mechanism use. Trace-level diagnostics further expose distinct bottlenecks across capabilities, demonstrating that mechanism access, effective mechanism use, and downstream performance are not interchangeable measures of agent capability. LiveMACEBench makes this distinction measurable, turning live markets from a performance leaderboard into a diagnostic environment for agent capability

In this paper, we explore the potential of Large Language Models (LLMs) Agents in playing the strategic social deduction game, Resistance Avalon. Players in Avalon are challenged not only to make informed decisions based on dynamically evolving game phases, but also to engage in discussions where they must deceive, deduce, and negotiate with other players. These characteristics make Avalon a compelling test-bed to study the decision-making and language-processing capabilities of LLM Agents. To facilitate research in this line, we introduce AvalonBench - a comprehensive game environment tailored for evaluating multi-agent LLM Agents. This benchmark incorporates: (1) a game environment for Avalon, (2) rule-based bots as baseline opponents, and (3) ReAct-style LLM agents with tailored prompts for each role. Notably, our evaluations based on AvalonBench highlight a clear capability gap. For instance, models like ChatGPT playing good-role got a win rate of 22.2% against rule-based bots playing evil, while good-role bot achieves 38.2% win rate in the same setting. We envision AvalonBench could be a good test-bed for developing more advanced LLMs (with self-playing) and agent frameworks that can effectively model the layered complexities of such game environments.

Autonomous agents have recently achieved remarkable progress across diverse domains, yet most evaluations focus on short-horizon, fully observable tasks. In contrast, many critical real-world tasks, such as large-scale software development, commercial investment, and scientific discovery, unfold in long-horizon and partially observable scenarios where success hinges on sustained reasoning, planning, memory management, and tool use. Existing benchmarks rarely capture these long-horizon challenges, leaving a gap in systematic evaluation. To bridge this gap, we introduce UltraHorizon a novel benchmark that measures the foundational capabilities essential for complex real-world challenges. We use exploration as a unifying task across three distinct environments to validate these core competencies. Agents are designed in long-horizon discovery tasks where they must iteratively uncover hidden rules through sustained reasoning, planning, memory and tools management, and interaction with environments. Under the heaviest scale setting, trajectories average 200k+ tokens and 400+ tool calls, whereas in standard configurations they still exceed 35k tokens and involve more than 60 tool calls on average. Our extensive experiments reveal that LLM-agents consistently underperform in these settings, whereas human participants achieve higher scores, underscoring a persistent gap in agents' long-horizon abilities. We also observe that simple scaling fails in our task. To better illustrate the failure of agents, we conduct an in-depth analysis of collected trajectories. We identify eight types of errors and attribute them to two primary causes: in-context locking and functional fundamental capability gaps. https://github.com/StarDewXXX/UltraHorizon{Our code will be available here.}

The advancement of large language model (LLM) based agents has shifted AI evaluation from single-turn response assessment to multi-step task completion in interactive environments. We present an empirical study evaluating frontier AI models on 150 workplace tasks within a realistic e-commerce RL environment from Surge. Our analysis reveals an empirically-derived hierarchy of agentic capabilities that models must master for real-world deployment: (1) tool use, (2) planning and goal formation, (3) adaptability, (4) groundedness, and (5) common-sense reasoning. Even the best-performing models fail approximately 40\% of the tasks, with failures clustering predictably along this hierarchy. Weaker models struggle with fundamental tool use and planning, whereas stronger models primarily fail on tasks requiring contextual inference beyond explicit instructions. We introduce a task-centric design methodology for RL environments that emphasizes diversity and domain expert contributions, provide detailed failure analysis, and discuss implications for agent development. Our findings suggest that while current frontier models can demonstrate coherent multi-step behavior, substantial capability gaps remain before achieving human-level task completion in realistic workplace settings.

AI agents deployed as persistent assistants must maintain correct beliefs as their information environment evolves. In practice, evidence is scattered across heterogeneous sources that often contradict one another, new information can invalidate earlier conclusions, and user preferences surface through corrections rather than explicit instructions. Existing benchmarks largely assume static, single-authority settings and do not evaluate whether agents can keep up with this complexity. We introduce ClawArena, a benchmark for evaluating AI agents in evolving information environments. Each scenario maintains a complete hidden ground truth while exposing the agent only to noisy, partial, and sometimes contradictory traces across multi-channel sessions, workspace files, and staged updates. Evaluation is organized around three coupled challenges: multi-source conflict reasoning, dynamic belief revision, and implicit personalization, whose interactions yield a 14-category question taxonomy. Two question formats, multi-choice (set-selection) and shell-based executable checks, test both reasoning and workspace grounding. The current release contains 64 scenarios across 8 professional domains, totaling 1{,}879 evaluation rounds and 365 dynamic updates. Experiments on five agent frameworks and five language models show that both model capability (15.4% range) and framework design (9.2%) substantially affect performance, that self-evolving skill frameworks can partially close model-capability gaps, and that belief revision difficulty is determined by update design strategy rather than the mere presence of updates. Code is available at https://github.com/aiming-lab/ClawArena.

AI agents are changing the requirements for document parsing. What matters is semantic correctness: parsed output must preserve the structure and meaning needed for autonomous decisions, including correct table structure, precise chart data, semantically meaningful formatting, and visual grounding. Existing benchmarks do not fully capture this setting for enterprise automation, relying on narrow document distributions and text-similarity metrics that miss agent-critical failures. We introduce ParseBench, a benchmark of {sim}2{,}000 human-verified pages from enterprise documents spanning insurance, finance, and government, organized around five capability dimensions: tables, charts, content faithfulness, semantic formatting, and visual grounding. Across 14 methods spanning vision-language models, specialized document parsers, and LlamaParse, the benchmark reveals a fragmented capability landscape: no method is consistently strong across all five dimensions. LlamaParse Agentic achieves the highest overall score at \agenticoverall\%, and the benchmark highlights the remaining capability gaps across current systems. Dataset and evaluation code are available on https://huggingface.co/datasets/llamaindex/ParseBench{HuggingFace} and https://github.com/run-llama/ParseBench{GitHub}.

Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination logic, and session-bound learning. We argue that this reflects a deeper absence: a principled organisational layer that governs how a workforce of agents is assembled, governed, and improved over time, decoupled from what individual agents know. To fill this gap, we introduce OneManCompany (OMC), a framework that elevates multi-agent systems to the organisational level. OMC encapsulates skills, tools, and runtime configurations into portable agent identities called Talents, orchestrated through typed organisational interfaces that abstract over heterogeneous backends. A community-driven Talent Market enables on-demand recruitment, allowing the organisation to close capability gaps and reconfigure itself dynamically during execution. Organisational decision-making is operationalised through an Explore-Execute-Review (E^2R) tree search, which unifies planning, execution, and evaluation in a single hierarchical loop: tasks are decomposed top-down into accountable units and execution outcomes are aggregated bottom-up to drive systematic review and refinement. This loop provides formal guarantees on termination and deadlock freedom while mirroring the feedback mechanisms of human enterprises. Together, these contributions transform multi-agent systems from static, pre-configured pipelines into self-organising and self-improving AI organisations capable of adapting to open-ended tasks across diverse domains. Empirical evaluation on PRDBench shows that OMC achieves an 84.67% success rate, surpassing the state of the art by 15.48 percentage points, with cross-domain case studies further demonstrating its generality.

Aligning Large Language Models (LLMs) for open-ended tasks is challenging because responses must satisfy multidimensional criteria without following a single correct generation trajectory. Existing rubric-based reinforcement learning (RL) methods compress fine-grained criterion-level feedback into scalar rewards, making persistent capability gaps difficult to target under limited on-policy exploration. We propose RISE-RL (Rubric-Informed Selective Exploration), which uses repeatedly missed rubric criteria to elicit privileged trajectories that are difficult to discover through unguided exploration alone. RISE-RL retains only trajectories whose complete-rubric reward exceeds the mean reward of natural rollouts, and then re-evaluates them under the original prompt to emphasize behaviors that remain weakly supported by the natural policy. The resulting guidance signal is optimized through a separate auxiliary objective and removed once its additional benefit diminishes. Experiments with 4B and 14B models across writing, chat, health, and science show that RISE-RL achieves the highest mean score on every evaluated benchmark under guidance-free evaluation. Compared with standard Rubric-RL, it improves the average score by 1.3 points at the 4B scale and 3.3 points at the 14B scale, including a 6.0-point gain on CreativeWriting-V3. It also improves creative-writing diversity and yields gains on objectively scored medical and scientific benchmarks. These results indicate that selective internalization through reward filtering and policy support shaping is effective for open-ended reinforcement learning.

True intelligence requires active capability acquisition, yet current LLM agents inject pre-defined tool schemas into prompts, reducing models to passive selectors and falling short of robust general-purpose agency. We introduce MCP-Zero, an active agent framework that restores tool discovery autonomy to LLMs themselves. Instead of overwhelming models with all available tools, MCP-Zero enables agents to actively identify capability gaps, and request specific tools on-demand, transforming them from large-scale retrievers into genuine autonomous agents. The framework operates through three core mechanisms: (1) Active Tool Request, where models autonomously generate structured requests specifying their exact tool requirements; (2) Hierarchical Semantic Routing, a two-stage algorithm that matches requests to relevant servers and tools through improved semantic alignment; (3) Iterative Capability Extension, enabling agents to progressively build cross-domain toolchains while maintaining minimal context footprint. We construct MCP-tools, a comprehensive dataset of 308 MCP servers and 2,797 tools from the official Model-Context-Protocol repository. Experiments demonstrate that MCP-Zero preserves agent autonomy while achieving substantial efficiency gains: (i) accurate tool selection from nearly 3k candidates across 248.1k tokens; (ii) 98\% reduction in token consumption on APIBank while maintaining high accuracy; and (iii) consistent multi-turn performance that scales with tool ecosystem growth. This work establishes active tool discovery as a fundamental design pattern for scalable autonomous agent systems.

Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result reporting. Despite their critical role in machine learning infrastructure, their operational challenges and engineering concerns have received limited attention so far. We present an empirical study of 57 evaluation harnesses, deriving a five-stage harness model and classifying 16,560 issues by workflow stage and root cause. Most harness operational challenges concentrate in the Specification stage (41.4% of issues), where harnesses integrate external models, datasets, and scoring judges. The three most frequent root causes of operational challenges are unimplemented features (24.3%), documentation gaps (20.3%), and missing input validation (17.2%), which together account for 61.7% of classified issues, spanning both defects in existing functionality and capability gaps that block intended workflows. Root causes also vary by workflow stage: environment incompatibility and external dependency breakage account for 36.2% of provisioning issues, whereas algorithmic error (25.9%) and validation gap (22.5%) dominate assessment issues. Together, these contributions establish an empirical foundation for treating evaluation engineering as a distinct software engineering concern.

Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. However, its efficacy can be limited due to the low predictive accuracy of the draft model, particularly when faced with diverse text inputs and a significant capability gap between the draft and target models. We introduce online speculative decoding (OSD) to address this challenge. The main idea is to continually update (multiple) draft model(s) on observed user query data using the abundant excess computational power in an LLM serving cluster. Given that LLM inference is memory-bounded, the surplus computational power in a typical LLM serving cluster can be repurposed for online retraining of draft models, thereby making the training cost-neutral. Since the query distribution of an LLM service is relatively simple, retraining on query distribution enables the draft model to more accurately predict the target model's outputs, particularly on data originating from query distributions. As the draft model evolves online, it aligns with the query distribution in real time, mitigating distribution shifts. We develop a prototype of online speculative decoding based on online knowledge distillation and evaluate it using both synthetic and real query data on several popular LLMs. The results show a substantial increase in the token acceptance rate by 0.1 to 0.65, which translates into 1.22x to 3.06x latency reduction.

Superalignment, where humans are weak supervisors of superhuman models, has become an important and widely discussed issue in the current era of rapid development of Large Language Models (LLMs). The recent work preliminarily studies this problem by using weak models to supervise strong models. It discovers that weakly supervised strong students can consistently outperform weak teachers towards the alignment target, leading to a weak-to-strong generalization phenomenon. However, we are concerned that behind such a promising phenomenon, whether there exists an issue of weak-to-strong deception, where strong models may deceive weak models by exhibiting well-aligned in areas known to weak models but producing misaligned behaviors in cases weak models do not know. We then take an initial step towards exploring this security issue in a specific but realistic multi-objective alignment case, where there may be some alignment targets conflicting with each other (e.g., helpfulness v.s. harmlessness). Such a conflict is likely to cause strong models to deceive weak models in one alignment dimension to gain high reward in other alignment dimension. Our experiments on both the reward modeling task and the preference optimization scenario indicate: (1) the weak-to-strong deception exists; (2) the deception phenomenon may intensify as the capability gap between weak and strong models increases. We also discuss potential solutions and find bootstrapping with an intermediate model can mitigate the deception to some extent. Our work highlights the urgent need to pay more attention to the true reliability of superalignment.

Large language models (LLMs) have shown increasing capability in problem-solving and decision-making, largely based on the step-by-step chain-of-thought reasoning processes. However, it has been increasingly challenging to evaluate the reasoning capability of LLMs. Concretely, existing outcome-based benchmarks begin to saturate and become less sufficient to monitor the progress. To this end, we present a process-based benchmark MR-BEN that demands a meta reasoning skill, where LMs are asked to locate and analyse potential errors in automatically generated reasoning steps. MR-BEN is a comprehensive benchmark comprising 5,975 questions collected from human experts, covering various subjects such as physics, chemistry, logic, coding, and more. Through our designed metrics for assessing meta-reasoning on this benchmark, we identify interesting limitations and weaknesses of current LLMs (open-source and closed-source models). For example, open-source models are seemingly comparable to GPT-4 on outcome-based benchmarks, but they lag far behind on our benchmark, revealing the underlying reasoning capability gap between them. Our dataset and codes are available on https://randolph-zeng.github.io/Mr-Ben.github.io/.

We present SmolTulu-1.7b-Instruct, referenced in this report as SmolTulu-DPO-1130, an instruction-tuned language model that adapts AllenAI's Tulu 3 post-training pipeline to enhance Huggingface's SmolLM2-1.7B base model. Through comprehensive empirical analysis using a 135M parameter model, we demonstrate that the relationship between learning rate and batch size significantly impacts model performance in a task-dependent manner. Our findings reveal a clear split: reasoning tasks like ARC and GSM8K benefit from higher learning rate to batch size ratios, while pattern recognition tasks such as HellaSwag and IFEval show optimal performance with lower ratios. These insights informed the development of SmolTulu, which achieves state-of-the-art performance among sub-2B parameter models on instruction following, scoring 67.7% on IFEval (Delta11%), and mathematical reasoning with 51.6% on GSM8K (Delta3.4%), with an alternate version achieving scoring 57.1% on ARC (Delta5.4%). We release our model, training recipes, and ablation studies to facilitate further research in efficient model alignment, demonstrating that careful adaptation of optimization dynamics can help bridge the capability gap between small and large language models.

Code performance optimization is paramount in real-world software engineering and critical for production-level systems. While Large Language Models (LLMs) have demonstrated impressive capabilities in code generation and bug fixing, their proficiency in enhancing code performance at the repository level remains largely unexplored. To address this gap, we introduce SWE-Perf, the first benchmark specifically designed to systematically evaluate LLMs on code performance optimization tasks within authentic repository contexts. SWE-Perf comprises 140 carefully curated instances, each derived from performance-improving pull requests from popular GitHub repositories. Each benchmark instance includes the relevant codebase, target functions, performance-related tests, expert-authored patches, and executable environments. Through a comprehensive evaluation of representative methods that span file-level and repo-level approaches (e.g., Agentless and OpenHands), we reveal a substantial capability gap between existing LLMs and expert-level optimization performance, highlighting critical research opportunities in this emerging field.

We introduce CMPhysBench, designed to assess the proficiency of Large Language Models (LLMs) in Condensed Matter Physics, as a novel Benchmark. CMPhysBench is composed of more than 520 graduate-level meticulously curated questions covering both representative subfields and foundational theoretical frameworks of condensed matter physics, such as magnetism, superconductivity, strongly correlated systems, etc. To ensure a deep understanding of the problem-solving process,we focus exclusively on calculation problems, requiring LLMs to independently generate comprehensive solutions. Meanwhile, leveraging tree-based representations of expressions, we introduce the Scalable Expression Edit Distance (SEED) score, which provides fine-grained (non-binary) partial credit and yields a more accurate assessment of similarity between prediction and ground-truth. Our results show that even the best models, Grok-4, reach only 36 average SEED score and 28% accuracy on CMPhysBench, underscoring a significant capability gap, especially for this practical and frontier domain relative to traditional physics. The code anddataset are publicly available at https://github.com/CMPhysBench/CMPhysBench.

Despite the rapid advancements in Multimodal Large Language Models (MLLMs), a critical question regarding their visual grounding mechanism remains unanswered: do these models genuinely ``read'' text embedded in images, or do they merely rely on parametric shortcuts in the text prompt? In this work, we diagnose this issue by introducing the Visualized-Question (VQ) setting, where text queries are rendered directly onto images to structurally mandate visual engagement. Our diagnostic experiments on Qwen2.5-VL reveal a startling capability-utilization gap: despite possessing strong OCR capabilities, models suffer a performance degradation of up to 12.7% in the VQ setting, exposing a deep-seated ``modality laziness.'' To bridge this gap, we propose SimpleOCR, a plug-and-play training strategy that imposes a structural constraint on the learning process. By transforming training samples into the VQ format with randomized styles, SimpleOCR effectively invalidates text-based shortcuts, compelling the model to activate and optimize its visual text extraction pathways. Empirically, SimpleOCR yields robust gains without architectural modifications. On four representative OOD benchmarks, it surpasses the base model by 5.4% and GRPO based on original images by 2.7%, while exhibiting extreme data efficiency, achieving superior performance with 30x fewer samples (8.5K) than recent RL-based methods. Furthermore, its plug-and-play nature allows seamless integration with advanced RL strategies like NoisyRollout to yield complementary improvements. Code is available at https://github.com/aiming-lab/SimpleOCR.

Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowledge distillation) struggle to correct the student's inherent errors. Fully on-policy methods (e.g., Generative Adversarial Distillation) solve this via adversarial training but introduce well-known training instability and crippling computational overhead. To address this dilemma, we propose SODA (Semi On-policy Distillation with Alignment), a highly efficient alternative motivated by the inherent capability gap between frontier teachers and much smaller base models. Because a compact student model's natural, zero-shot responses are almost strictly inferior to the powerful teacher's targets, we can construct a highly effective contrastive signal simply by pairing the teacher's optimal response with a one-time static snapshot of the student's outputs. This demonstrates that exposing the small student to its own static inferior behaviors is sufficient for high-quality distribution alignment, eliminating the need for costly dynamic rollouts and fragile adversarial balancing. Extensive evaluations across four compact Qwen2.5 and Llama-3 models validate this semi on-policy paradigm. SODA matches or outperforms the state-of-the-art methods on 15 out of 16 benchmark results. More importantly, it achieves this superior distillation quality while training 10 times faster, consuming 27% less peak GPU memory, and completely eliminating adversarial instability.

The significance of cross-view 3D geometric modeling capabilities for autonomous driving is self-evident, yet existing Vision-Language Models (VLMs) inherently lack this capability, resulting in their mediocre performance. While some promising approaches attempt to mitigate this by constructing Q&A data for auxiliary training, they still fail to fundamentally equip VLMs with the ability to comprehensively handle diverse evaluation protocols. We thus chart a new course, advocating for the infusion of VLMs with the cross-view geometric grounding of mature 3D foundation models, closing this critical capability gap in autonomous driving. In this spirit, we propose a novel architecture, VGGDrive, which empowers Vision-language models with cross-view Geometric Grounding for autonomous Driving. Concretely, to bridge the cross-view 3D geometric features from the frozen visual 3D model with the VLM's 2D visual features, we introduce a plug-and-play Cross-View 3D Geometric Enabler (CVGE). The CVGE decouples the base VLM architecture and effectively empowers the VLM with 3D features through a hierarchical adaptive injection mechanism. Extensive experiments show that VGGDrive enhances base VLM performance across five autonomous driving benchmarks, including tasks like cross-view risk perception, motion prediction, and trajectory planning. It's our belief that mature 3D foundation models can empower autonomous driving tasks through effective integration, and we hope our initial exploration demonstrates the potential of this paradigm to the autonomous driving community.

Recent diffusion models achieve strong photorealism and fluency in video generation, yet remain fragile under abstract, sparse or complex conditions, leading to poor performance in professional production workflows such as storyboard sketches and clay render conditions. Existing video generation models, either inject conditions through adapters or couple a generic vision-language model (VLM) within a diffusion backbone, leaving a capability gap and failing to produce the videos that align with the user's creative intent. We present CogOmniControl, a reasoning-driven framework that factorizes controllable video generation into creative intent cognition and generation. Specifically, we train a specialized CogVLM using authentic anime production data. Compared to generic VLMs, it generates more professional and clear outputs, accurately cognizing user creative intent from sparse and abstract conditions and tuning these cues into dense reasoning output. Besides, CogOmniDiT unifies the controls from various conditions through in-context generation and is aligned to the CogVLM reasoning outputs via reinforcement learning. Furthermore, leveraging CogVLM's robust capability in guiding video generation, we release its potential in planning specific evaluators and enable a Best-of-N selection for the generated videos. This integration transforms the entire framework into a closed-loop "harness-like" architecture. We further introduce CogReasonBench and CogControlBench, built from professional workflows data that carry genuine creative intent rather than simulated ones. Experiments on two benchmarks show that CogOmniControl surpassed the existing open-source models. The project website: https://um-lab.github.io/CogOmniControl/

Model developers implement safeguards in frontier models to prevent misuse, for example, by employing classifiers to filter dangerous outputs. In this work, we demonstrate that even robustly safeguarded models can be used to elicit harmful capabilities in open-source models through elicitation attacks. Our elicitation attacks consist of three stages: (i) constructing prompts in adjacent domains to a target harmful task that do not request dangerous information; (ii) obtaining responses to these prompts from safeguarded frontier models; (iii) fine-tuning open-source models on these prompt-output pairs. Since the requested prompts cannot be used to directly cause harm, they are not refused by frontier model safeguards. We evaluate these elicitation attacks within the domain of hazardous chemical synthesis and processing, and demonstrate that our attacks recover approximately 40% of the capability gap between the base open-source model and an unrestricted frontier model. We then show that the efficacy of elicitation attacks scales with the capability of the frontier model and the amount of generated fine-tuning data. Our work demonstrates the challenge of mitigating ecosystem level risks with output-level safeguards.

Recent progress in promptable segmentation has shifted visual perception from object-level localization toward concept-level understanding. However, the notion of a concept remains under-specified, making it unclear whether current methods truly generalize beyond category recognition. In this work, we formalize generalized concept segmentation through a three-level taxonomy consisting of context-independent (CI), context-dependent (CD), and context-reasoning (CR) concepts, which reveals a clear capability gap across increasing levels of cognitive complexity. To address this challenge, we propose ConceptSeg-R1, a unified framework that reformulates concept segmentation as rule-induced concept grounding. At the core of our method is Meta-GRPO, a meta-reinforcement learning mechanism that learns transferable task rules from visual demonstrations and verifies them through proxy reasoning. The inferred reasoning states are then translated into segmentation-ready concept prompts via a lightweight concept translation module, enabling deductive application to target images. A shortcut routing strategy further preserves the native efficiency of segmentation models on simple cases. To systematically evaluate generalized concept segmentation, we conduct extensive experiments across diverse CI, CD, and CR concept segmentation benchmarks spanning natural, industrial, medical and reasoning-intensive domains. Without bells and whistles, ConceptSeg-R1 achieves strong performance across the full concept hierarchy while maintaining the native capability of promptable segmentation backbones. As an initial step toward segmenting any concept, we hope ConceptSeg-R1 can serve as a practical baseline for advancing segmentation from object-level prediction toward concept-level understanding.

On-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. To furnish high-quality supervision sources and thereby elevate the performance frontier of distillation, an intuitive direction is to infuse privileged information to either teacher or student itself. However, this additional input induces a potential failure mode we dub privilege illusion: a pattern that conflates the transferable capability gap that students are meant to close, and the information asymmetry gap that can only be mimicked but never replicated. This issue is further amplified by the inherent non-uniformity of token-level supervision, where only a small subset of tokens carries pivotal capability-bearing signals. To this end, we propose DOPD, an advantage-aware dual distillation paradigm that dynamically routes token-level supervision between privileged teacher and privileged student policies based on their advantage gap and relative probabilities. Each token receives supervision of different strength, objective, and strategy from either teacher or student itself, which transfers credible capability while simultaneously receiving auxiliary signals, to alleviate privilege illusion. Extensive experiments on both large language model (LLM) and vision-language model (VLM) settings demonstrate that DOPD consistently outperforms Vanilla OPD and other counterparts. Further results on stability, robustness, continual learning, and out-of-distribution tasks validate its superiority.

Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets. We reveal a critical inefficiency in this approach: up to 69% of the prompts in standard chart / document reasoning datasets are effectively zero-delta, meaning the teacher and student already induce the exact same answer distribution. Training on these prompts provides minimal learning signal, causing student improvement to rapidly saturate regardless of data scale. To escape the zero-delta trap, we return to first principles: distillation fundamentally minimizes distributional divergence, and thus a prompt is valuable only if it exposes a functional capability gap between the teacher and student. We quantify this gap through answer divergence (Δ), demonstrating that non-zero divergence is critical for effective scaling. Building on this insight, we propose a staged synthesis pipeline that repurposes existing datasets as seeds, actively targeting student failure modes to produce better prompts. The result is DeltaPrompts, a diverse dataset of 200k synthetic, high-divergence reasoning problems. We evaluate DeltaPrompts across three distinct settings: on-policy distillation with the target teacher-student pair, transfer to a novel model family without regenerating the data, and off-policy fine-tuning of a non-reasoning model. Across all scenarios, DeltaPrompts drives substantial gains, yielding up to 15% relative improvement even on top of a highly-optimized reasoning model (e.g., Qwen3-VL-8B-Thinking) -- averaged over 10 benchmarks spanning chart, document and perception-centric reasoning.

Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all opensource agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.

Transcending human cognitive limitations represents a critical frontier in LLM training. Proprietary agentic systems like DeepResearch have demonstrated superhuman capabilities on extremely complex information-seeking benchmarks such as BrowseComp, a feat previously unattainable. We posit that their success hinges on a sophisticated reasoning pattern absent in open-source models: the ability to systematically reduce extreme uncertainty when navigating vast information landscapes. Based on this insight, we introduce WebSailor, a complete post-training methodology designed to instill this crucial capability. Our approach involves generating novel, high-uncertainty tasks through structured sampling and information obfuscation, RFT cold start, and an efficient agentic RL training algorithm, Duplicating Sampling Policy Optimization (DUPO). With this integrated pipeline, WebSailor significantly outperforms all open-source agents in complex information-seeking tasks, matching proprietary agents' performance and closing the capability gap.

The prevailing video retrieval paradigm is structurally misaligned, as narrow benchmarks incentivize correspondingly limited data and single-task training. Therefore, universal capability is suppressed due to the absence of a diagnostic evaluation that defines and demands multi-dimensional generalization. To break this cycle, we introduce a framework built on the co-design of evaluation, data, and modeling. First, we establish the Universal Video Retrieval Benchmark (UVRB), a suite of 16 datasets designed not only to measure performance but also to diagnose critical capability gaps across tasks and domains. Second, guided by UVRB's diagnostics, we introduce a scalable synthesis workflow that generates 1.55 million high-quality pairs to populate the semantic space required for universality. Finally, we devise the Modality Pyramid, a curriculum that trains our General Video Embedder (GVE) by explicitly leveraging the latent interconnections within our diverse data. Extensive experiments show GVE achieves state-of-the-art zero-shot generalization on UVRB. In particular, our analysis reveals that popular benchmarks are poor predictors of general ability and that partially relevant retrieval is a dominant but overlooked scenario. Overall, our co-designed framework provides a practical path to escape the limited scope and advance toward truly universal video retrieval.

While current Computer Use Agent (CUA) benchmarks measure task completion effectively, they provide limited assessment of enterprise deployment readiness, emphasizing functional correctness over the operational reliability required for production systems. We present UI-CUBE (UiPath Computer Use BEnchmark), a systematic benchmark comprising 226 tasks across two difficulty tiers designed to expose fundamental architectural limitations in current CUAs. Our evaluation covers simple UI interactions (136 tasks) and complex workflows including copy-paste tasks (50 tasks) and enterprise application scenarios (40 tasks), with systematic interface variation coverage, multi-resolution testing and automated validation of task success through the application state. Evaluation of five state-of-the-art models reveals a sharp capability cliff rather than gradual performance degradation. Simple UI interactions achieve 67-85% success rates (compared to 97.9% human performance), but complex workflows drop precipitously to 9-19%. Human evaluators with no prior application experience achieve only 61.2% on complex tasks despite near-perfect performance on simple tasks, establishing realistic performance ceilings. This discontinuous performance pattern -- where agents achieve 68-87% of human performance on simple tasks but only 15-32% on complex workflows -- indicates fundamental architectural limitations in memory management, hierarchical planning, and state coordination rather than incremental capability gaps addressable through better training or prompting. UI-CUBE functions as an enterprise-readiness diagnostic, revealing that while current CUAs can manipulate individual interface elements, they cannot yet function as reliable workflow automation tools. These findings provide architectural insights essential for developing production-ready CUAs capable of managing complex, multi-step enterprise processes.

Enabling Large Language Models (LLMs) to reliably invoke external tools remains a critical bottleneck for autonomous agents. Existing approaches suffer from three fundamental challenges: expensive human annotation for high-quality trajectories, poor generalization to unseen tools, and quality ceilings inherent in single-model synthesis that perpetuate biases and coverage gaps. We introduce InfTool, a fully autonomous framework that breaks these barriers through self-evolving multi-agent synthesis. Given only raw API specifications, InfTool orchestrates three collaborative agents (User Simulator, Tool-Calling Assistant, and MCP Server) to generate diverse, verified trajectories spanning single-turn calls to complex multi-step workflows. The framework establishes a closed loop: synthesized data trains the model via Group Relative Policy Optimization (GRPO) with gated rewards, the improved model generates higher-quality data targeting capability gaps, and this cycle iterates without human intervention. Experiments on the Berkeley Function-Calling Leaderboard (BFCL) demonstrate that InfTool transforms a base 32B model from 19.8% to 70.9% accuracy (+258%), surpassing models 10x larger and rivaling Claude-Opus, and entirely from synthetic data without human annotation.

Test-time policy adaptation for multi-turn interactions (T2PAM) is essential for aligning Large Language Models (LLMs) with dynamic user needs during inference time. However, existing paradigms commonly treat test-time adaptation as a single-axis problem, either purely refining instructions (Prompt Engineering) or only adjusting weights (Test-Time Training), ignoring that interaction failures stem from a coupled mix of ambiguity and incapacity. We argue that these two optimization paths are not merely additive but synergistic: semantic clarity acts as a pre-conditioner for effective parameter updates. To this end, we propose ROSA2, a framework that reformulates interaction as a joint optimization problem over the heterogeneous space of Words and Weights. By mathematically decomposing the error signal, ROSA2 utilizes textual gradients to rectify intent ambiguity and parameter updates to bridge capability gaps. Theoretically, we prove that this co-adaptation strictly reduces the required parameter shift for convergence. Empirically, ROSA2 outperforms state-of-the-art baselines by 30% on MATH while reducing interaction turns by 40%, demonstrating that refining the context unlocks the true potential of parameter updates.

Recent advances in large language models (LLMs) have enabled agentic systems that translate natural language intent into executable scientific visualization (SciVis) tasks. Despite rapid progress, the community lacks a principled and reproducible benchmark for evaluating these emerging SciVis agents in realistic, multi-step analysis settings. We present SciVisAgentBench, a comprehensive and extensible benchmark for evaluating scientific data analysis and visualization agents. Our benchmark is grounded in a structured taxonomy spanning four dimensions: application domain, data type, complexity level, and visualization operation. It currently comprises 108 expert-crafted cases covering diverse SciVis scenarios. To enable reliable assessment, we introduce a multimodal outcome-centric evaluation pipeline that combines LLM-based judging with deterministic evaluators, including image-based metrics, code checkers, rule-based verifiers, and case-specific evaluators. We also conduct a validity study with 12 SciVis experts to examine the agreement between human and LLM judges. Using this framework, we evaluate representative SciVis agents and general-purpose coding agents to establish initial baselines and reveal capability gaps. SciVisAgentBench is designed as a living benchmark to support systematic comparison, diagnose failure modes, and drive progress in agentic SciVis. The benchmark is available at https://scivisagentbench.github.io/.

Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling Attacks. Unlike adversarial perturbations (for misclassification) and adversarial jailbreaks (for harmful output generation), adversarial smuggling exploits the Human-AI capability gap. It encodes harmful content into human-readable visual formats that remain AI-unreadable, thereby evading automated detection and enabling the dissemination of harmful content. We classify smuggling attacks into two pathways: (1) Perceptual Blindness, disrupting text recognition; and (2) Reasoning Blockade, inhibiting semantic understanding despite successful text recognition. To evaluate this threat, we constructed SmuggleBench, the first comprehensive benchmark comprising 1,700 adversarial smuggling attack instances. Evaluations on SmuggleBench reveal that both proprietary (e.g., GPT-5) and open-source (e.g., Qwen3-VL) state-of-the-art models are vulnerable to this threat, producing Attack Success Rates (ASR) exceeding 90%. By analyzing the vulnerability through the lenses of perception and reasoning, we identify three root causes: the limited capabilities of vision encoders, the robustness gap in OCR, and the scarcity of domain-specific adversarial examples. We conduct a preliminary exploration of mitigation strategies, investigating the potential of test-time scaling (via CoT) and adversarial training (via SFT) to mitigate this threat. Our code is publicly available at https://github.com/zhihengli-casia/smugglebench.

Synthesizing supervised finetuning (SFT) data from language models (LMs) to teach smaller models multilingual tasks has become increasingly common. However, teacher model selection is often ad hoc, typically defaulting to the largest available option, even though such models may have significant capability gaps in non-English languages. This practice can result in poor-quality synthetic data and suboptimal student downstream performance. In this work, we systematically characterize what makes an effective multilingual teacher. We measure intrinsic measures of data quality with extrinsic student model performance in a metric we call Polyglot Score; evaluating 10 LMs across 6 typologically diverse languages, generating over 1.4M SFT examples and training 240 student models. Among the models tested, Gemma 3 27B and Aya Expanse 32B emerge as consistently effective teachers across different student base model families. Further analyses reveal that model scale alone does not significantly predict teacher effectiveness; instead, data qualities such as prompt diversity, length, and response fluency capture over 93.3% of variance in intrinsic data quality and predict student performance. Finally, we provide practical recommendations, including matching the model families of teacher-student pairs and translating from or responding to existing prompts, which can yield improvements for less-resourced languages. We hope that our work advances data-centric research in multilingual synthetic data and LM development.

Benchmarks within the OpenClaw ecosystem have thus far evaluated exclusively assistant-level tasks, leaving the academic-level capabilities of OpenClaw largely unexamined. We introduce AcademiClaw, a bilingual benchmark of 80 complex, long-horizon tasks sourced directly from university students' real academic workflows -- homework, research projects, competitions, and personal projects -- that they found current AI agents unable to solve effectively. Curated from 230 student-submitted candidates through rigorous expert review, the final task set spans 25+ professional domains, ranging from olympiad-level mathematics and linguistics problems to GPU-intensive reinforcement learning and full-stack system debugging, with 16 tasks requiring CUDA GPU execution. Each task executes in an isolated Docker sandbox and is scored on task completion by multi-dimensional rubrics combining six complementary techniques, with an independent five-category safety audit providing additional behavioral analysis. Experiments on six frontier models show that even the best achieves only a 55\% pass rate. Further analysis uncovers sharp capability boundaries across task domains, divergent behavioral strategies among models, and a disconnect between token consumption and output quality, providing fine-grained diagnostic signals beyond what aggregate metrics reveal. We hope that AcademiClaw and its open-sourced data and code can serve as a useful resource for the OpenClaw community, driving progress toward agents that are more capable and versatile across the full breadth of real-world academic demands. All data and code are available at https://github.com/GAIR-NLP/AcademiClaw.

Large Language Models (LLMs) have the potential to accelerate small molecule drug design due to their ability to reason about information from diverse sources and formats. However, their practical utility remains unclear due to the lack of benchmarks that reflect real-world scenarios. In this work, we introduce a suite of chemically-grounded tasks spanning molecular property prediction, molecular representation transformations, and molecular design. Importantly, we formulate these tasks as reinforcement learning (RL) environments, enabling a unified approach for evaluation and post-training. Across three model families, we find that frontier models are increasingly proficient at chemical tasks, but that there is significant room for improvement, especially in experimental settings with low data. Critically, we show that RL-based post-training can substantially improve performance. A smaller model post-trained on our environments becomes competitive with state-of-the-art frontier models, despite a significantly weaker base model. This suggests a practical route toward employing LLMs in drug discovery; by combining carefully-designed evaluation tasks with targeted post-training, we can both elucidate and close critical capability gaps.

As LLM agents tackle increasingly complex tasks, a critical question is whether they can maintain strategic coherence over long horizons: planning under uncertainty, learning from delayed feedback, and adapting when early mistakes compound. We introduce YC-Bench, a benchmark that evaluates these capabilities by tasking an agent with running a simulated startup over a one-year horizon spanning hundreds of turns. The agent must manage employees, select task contracts, and maintain profitability in a partially observable environment where adversarial clients and growing payroll create compounding consequences for poor decisions. We evaluate 12 models, both proprietary and open source, across 3 seeds each. Only three models consistently surpass the starting capital of \200K, with Claude Opus 4.6 achieving the highest average final funds at 1.27 M, followed by GLM-5 at \1.21 M at 11\times lower inference cost. Scratchpad usage, the sole mechanism for persisting information across context truncation, is the strongest predictor of success, and adversarial client detection is the primary failure mode, accounting for 47\% of bankruptcies. Our analysis reveals that frontier models still fail through distinct failure modes such as over-parallelization, demonstrating the capability gaps for long-horizon performance. YC-Bench$ is open-source, reproducible, and configurable.

Training computer-use agents (CUAs) -- models that interact with graphical desktops through screenshots and keyboard/mouse actions -- requires large-scale, diverse trajectory data collected in full desktop environments. The largest public resource, AgentNet (22.5K human trajectories), leads to negative transfer when used for supervised fine-tuning (SFT): continuing training UI-TARS 7B on AgentNet causes OSWorld success rate to fall from 26.3% to 8-10%. We present ProCUA-SFT, a dataset of 3.1M step-level SFT samples distilled from 93K synthetic trajectories across 2,484 application combinations. The dataset is produced by a fully automated pipeline that (i) synthesizes grounded tasks on live desktops seeded with real-world content -- 912 spreadsheets from SpreadsheetBench, approximately 10K permissively-licensed presentations from Zenodo10K, and multi-application OSWorld configs -- and (ii) verifies each task's feasibility through binary precondition checking before rollout. A single VLM (Kimi-K2.5) serves as goal generator, precondition judge, and trajectory executor, eliminating planner-actor capability gaps. Each trajectory is expanded into step-prefix samples that exactly reproduce the context layout seen at inference time. Fine-tuning UI-TARS 7B on ProCUA-SFT for one epoch yields 45.0% on OSWorld -- an 18.7 percentage-point improvement over the base model and over 35% above AgentNet-trained counterparts. A subset of ProCUA was incorporated into the training data for the Nemotron 3 Nano Omni model, contributing to its computer-use capabilities.

Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-evolution in expert domains. Existing self-evolving skill methods construct skills internally from the model's parametric knowledge or trajectories, and are therefore bounded by what the model already knows. However, the domain conventions and standard procedures underlying professional skills often lie beyond this boundary and are hard to elicit from the agent alone. To address this issue, we therefore propose a novel framework, Search2Skill, that automatically identifies the agent's capability gaps, searches external sources to address them, and distills the retrieved evidence into structured, reusable skills. Specifically, Search2Skill is optimized by a rubric-based reinforcement learning scheme that jointly improves when to search, how to search, and how to generate skills. Experiments on eight expert-level domains from three benchmarks show that Search2Skill consistently outperforms both search-augmented and trajectory-based skill-learning baselines under both streaming and held-out evaluation protocols. Further analyses show that the gains arise from skill abstraction rather than raw retrieved evidence, and that the acquired skills transfer across model scales.

General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To investigate this, we introduce RobotWorld, a challenging simulation testbed for robot use: turning instructions and observations into physical task execution through robot interfaces. Its 84 tasks span manipulation, mobile manipulation, locomotion, driving, and aerial control, with explicit interaction budgets and executable success checks. By analysing task outcomes alongside execution traces, we identify both the capabilities that transfer and the gaps that prevent reliable completion. Furthermore, we find that current agents can construct sophisticated perception and control workflows, including image segmentation, camera calibration, spatial estimation, and dynamics-based computation. These capabilities, however, do not consistently compose into successful behaviour: agents lose task-relevant object states despite reaching commanded poses, fail to correct ineffective actions, recover too late, or mistake unfinished tasks for completion. This uneven transfer also differs across models: Astra succeeds more often on spatial and constrained-contact goals, whereas Opus 5.5 succeeds more often on continuous-balance and timed-interaction goals. By linking these outcomes to execution behaviour, RobotWorld provides both a rigorous proving ground and an empirical account of the remaining capability gaps, thereby establishing concrete targets for training and designing more reliable physical-world agents.

We introduce SAIL, an open model with 35B total and 3B active parameters for literature research, scientific coding, and multi-step research workflows. SAIL is developed through a science-aware improvement loop: agents built on frontier AI models analyze its task failures and construct training tasks that address the underlying capability gaps. The diagnosis examines search and evidence selection in literature tasks, scientific assumptions and reasoning in coding, and planning and revision in longer investigations. The agents draw on paper collections and scientific code repositories to build problems, interaction trajectories, and executable tasks with the required environments and tools. We repeat this loop over multiple development cycles and train SAIL through supervised fine-tuning, specialist training, multi-teacher on-policy distillation, and agentic reinforcement learning. SAIL achieves competitive performance across scientific research tasks with substantially fewer parameters than leading open-weight models.

Large Multimodal Models (LMMs) have demonstrated impressive performance across numerous academic benchmarks. However, fine-tuning still remains essential to achieve satisfactory performance on downstream tasks, while the task-specific tuning samples are usually not readily available or expensive and time-consuming to obtain. To address this, we propose an error-driven data-efficient tuning framework that aims to efficiently adapt generic LMMs to newly emerging tasks without requiring any task-specific training samples. In our approach, a generic LMM, acting as a student model, is first evaluated on a small validation set of the target task, and then a more powerful model, acting as a teacher model, identifies the erroneous steps within the student model's reasoning steps and analyzes its capability gaps from fully addressing the target task. Based on these gaps, targeted training samples are further retrieved from existing task-agnostic datasets to tune the student model and tailor it to the target task. We perform extensive experiments across three different training data scales and seven tasks, demonstrating that our training paradigm significantly and efficiently improves LMM's performance on downstream tasks, achieving an average performance boost of 7.01%.

While Large Language Model (LLM) agents have achieved remarkable progress in complex reasoning tasks, evaluating their performance in real-world environments has become a critical problem. Current benchmarks, however, are largely restricted to idealized simulations, failing to address the practical demands of specialized domains like advertising and marketing analytics. In these fields, tasks are inherently more complex, often requiring multi-round interaction with professional marketing tools. To address this gap, we propose AD-Bench, a benchmark designed based on real-world business requirements of advertising and marketing platforms. AD-Bench is constructed from real user marketing analysis requests, with domain experts providing verifiable reference answers and corresponding reference tool-call trajectories. The benchmark categorizes requests into three difficulty levels (L1-L3) to evaluate agents' capabilities under multi-round, multi-tool collaboration. Experiments show that on AD-Bench, Gemini-3-Pro achieves Pass@1 = 68.0% and Pass@3 = 83.0%, but performance drops significantly on L3 to Pass@1 = 49.4% and Pass@3 = 62.1%, with a trajectory coverage of 70.1%, indicating that even state-of-the-art models still exhibit substantial capability gaps in complex advertising and marketing analysis scenarios. AD-Bench provides a realistic benchmark for evaluating and improving advertising marketing agents, the leaderboard and code can be found at https://github.com/Emanual20/adbench-leaderboard.

Large language models are increasingly expected to serve as general-purpose agents that interact with external, stateful tool environments. The Model Context Protocol (MCP) and broader agent skills offer a unified interface for connecting agents with scalable real-world services, but training robust agents remains limited by the lack of realistic environments and principled mechanisms for life-long learning. In this paper, we present Agent-World, a self-evolving training arena for advancing general agent intelligence through scalable environments. Agent-World has two main components: (1) Agentic Environment-Task Discovery, which autonomously explores topic-aligned databases and executable tool ecosystems from thousands of real-world environment themes and synthesizes verifiable tasks with controllable difficulty; and (2) Continuous Self-Evolving Agent Training, which combines multi-environment reinforcement learning with a self-evolving agent arena that automatically identifies capability gaps through dynamic task synthesis and drives targeted learning, enabling the co-evolution of agent policies and environments. Across 23 challenging agent benchmarks, Agent-World-8B and 14B consistently outperforms strong proprietary models and environment scaling baselines. Further analyses reveal scaling trends in relation to environment diversity and self-evolution rounds, offering insights for building general agent intelligence.

Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to learn, and determine whether they have actually improved. In contrast, existing work on LLM self-evolution typically begins with tasks and evaluation metrics specified by humans, reducing self-evolution to optimizing an explicit objective rather than deciding what and how to learn. We introduce ASPIRE, a benchmark for vague-goal-driven self-evolution. ASPIRE provides only a natural-language capability goal while downstream evaluation tasks remain hidden. The agent must operationalize the goal by choosing data and update methods, constructing training and validation signals, and deciding when to evaluate. ASPIRE supports both model-weight and agent-harness evolution in a unified interactive environment and evaluates the resulting systems on a hidden, expert-authored set of 520 items spanning six goals. Our experiments show that vague goals redirect search effort toward goal interpretation. Current agents routinely complete training and harness-editing loops, but weight-level gains remain sparse and unstable, and the strongest evolved harness remains below the engineered Qwen-Agent reference. Agents often train on mismatched data and trust narrow self-evaluations, so local gains fail to transfer to hidden evaluation and continued search and training can erase earlier improvements.

Can LLM agents improve decision-making through self-generated memory without gradient updates? We propose FORGE (Failure-Optimized Reflective Graduation and Evolution), a staged, population-based protocol that evolves prompt-injected natural-language memory for hierarchical ReAct agents. FORGE wraps a Reflexion-style inner loop, where a dedicated reflection agent (using the same underlying LLM, no distillation from a stronger model) converts failed trajectories into reusable knowledge artifacts: textual heuristics (Rules), few-shot demonstrations (Examples), or both (Mixed), with an outer loop that propagates the best-performing instance's memory to the population between stages and freezes converged instances via a graduation criterion. We evaluate on CybORG CAGE-2, a stochastic network-defense POMDP at a 30-step horizon against the B-line attacker, where all four tested LLM families (Gemini-2.5-Flash-Lite, Grok-4-Fast, Llama-4-Maverick, Qwen3-235B) exhibit strongly negative, heavy-tailed zero-shot rewards. Compared against both a zero-shot baseline and a Reflexion baseline (isolated single-stream learning), FORGE improves average evaluation return by 1.7-7.7times over zero-shot and by 29-72% over Reflexion in all 12 model-representation conditions, reducing major-failure rates (below -100) to as low as sim1%. We find that (1) population broadcast is critical mechanism, with a no-graduation ablation confirming that broadcast carries the performance gains while graduation primarily saves compute; (2) Examples achieves the strongest returns for three of four models, Rules offers the best cost-reliability profile with sim40% fewer tokens; and (3) weaker baseline models benefit disproportionately, suggesting FORGE may mitigate capability gaps rather than amplify strong models. All evidence is confined to CAGE-2 B-line; cross-family findings are directional evidence.

Multi-teacher on-policy distillation (M-OPD) has emerged as a promising paradigm for consolidating domain-specialized reinforcement learning (RL) experts into a single generalist student via dense, token-level reward supervision. Despite its practical success, the optimization dynamics governing multi-teacher capability integration remain poorly understood, and open, rigorously reproducible recipes are conspicuously lacking. In this work, we establish a controlled M-OPD benchmark on SmolLM3-3B-Base with oracle routing, isolating capability integration from routing ambiguity. Our investigation reveals a pronounced capability integration gap: standard M-OPD captures only 35.6% of the available headroom relative to a domain-routed oracle ensemble, with concise tasks such as instruction following suffering severe degradation and premature stagnation. Crucially, we show that this failure stems not from gradient conflict, but from a severe misallocation of the token-level optimization budget. This pathology is driven by three orthogonal factors: structural sequence-length disparities across domains, dynamic convergence drift due to non-uniform learning rates, and multi-step reward staleness from asynchronous policy updates. To resolve these imbalances, we introduce Open-MOPD, a principled framework incorporating token-share balancing, gap-aware dynamic budget allocation, and student reward refresh. Together, these mechanisms systematically restore cross-domain balance, elevating headroom recovery from 35.6% to 83.4% in a single deployable student. We fully open-source our end-to-end post-training recipe, training trajectories, and evaluation suites on an academically accessible hardware budget.

AI systems increasingly produce fluent, correct, end-to-end outcomes. Over time, this erodes users' ability to explain, verify, or intervene. We define this divergence as the Capability-Comprehension Gap: a decoupling where assisted performance improves while users' internal models deteriorate. This paper argues that prevailing approaches to transparency, user control, literacy, and governance do not define the foundational understanding humans must retain for oversight under sustained AI delegation. To formalize this, we define the Cognitive Integrity Threshold (CIT) as the minimum comprehension required to preserve oversight, autonomy, and accountable participation under AI assistance. CIT does not require full reasoning reconstruction, nor does it constrain automation. It identifies the threshold beyond which oversight becomes procedural and contestability fails. We operatinalize CIT through three functional dimensions: (i) verification capacity, (ii) comprehension-preserving interaction, and (iii) institutional scaffolds for governance. This motivates a design and governance agenda that aligns human-AI interaction with cognitive sustainability in responsibility-critical settings.

We introduce ResearchGym, a benchmark and execution environment for evaluating AI agents on end-to-end research. To instantiate this, we repurpose five oral and spotlight papers from ICML, ICLR, and ACL. From each paper's repository, we preserve the datasets, evaluation harness, and baseline implementations but withhold the paper's proposed method. This results in five containerized task environments comprising 39 sub-tasks in total. Within each environment, agents must propose novel hypotheses, run experiments, and attempt to surpass strong human baselines on the paper's metrics. In a controlled evaluation of an agent powered by GPT-5, we observe a sharp capability--reliability gap. The agent improves over the provided baselines from the repository in just 1 of 15 evaluations (6.7%) by 11.5%, and completes only 26.5% of sub-tasks on average. We identify recurring long-horizon failure modes, including impatience, poor time and resource management, overconfidence in weak hypotheses, difficulty coordinating parallel experiments, and hard limits from context length. Yet in a single run, the agent surpasses the solution of an ICML 2025 Spotlight task, indicating that frontier agents can occasionally reach state-of-the-art performance, but do so unreliably. We additionally evaluate proprietary agent scaffolds including Claude Code (Opus-4.5) and Codex (GPT-5.2) which display a similar gap. ResearchGym provides infrastructure for systematic evaluation and analysis of autonomous agents on closed-loop research.

PyMOLfold is a flexible and open-source plugin designed to seamlessly integrate AI-based protein structure prediction and visualization within the widely used PyMOL molecular graphics system. By leveraging state-of-the-art protein folding models such as ESM3, Boltz-1, and Chai-1, PyMOLfold allows researchers to directly predict protein tertiary structures from amino acid sequences without requiring external tools or complex workflows. Furthermore, with certain models, users can provide a SMILES string of a ligand and have the small molecule placed in the protein structure. This unique capability bridges the gap between computational folding and structural visualization, enabling users to input a primary sequence, perform a folding prediction, and immediately explore the resulting 3D structure within the same intuitive platform.

Large language models can reproduce training data, but existing memorization evaluations mostly measure whether models can be forced to do so, rather than whether they do so under ordinary use. We introduce PropMe, a propensity-aware framework for memorization evaluation that contrasts prefix-based capability attacks with non-adversarial evaluations. We propose a metric transformation that, applied to existing functions, allows to create propensity metrics. We further introduce SimpleTrace, a lightweight tracing pipeline built on infini-gram that deterministically attributes model generations to large-scale training corpora and computes verbatim, near-verbatim, and propensity-transformed memorization metrics. Evaluating two fully-open models: Comma and DFM Decoder on two datasets: Common Pile and Dynaword in two languages, we find a consistent gap between capability and propensity: prefix attacks elicit substantially stronger memorization signals than generic or dataset-specific prompts, while propensity scores remain low overall. Thus, the models can reveal training data when directly elicited, but rarely do so in more common non-adversarial settings. We also find that DFM Decoder, which is continually pre-trained from Comma, exhibits reduced memorization and memorization propensity for Common Pile, confirming that memorization capability can decrease when later training emphasizes partially different data. Our results suggest, and we encourage, that memorization audits should report both worst-case extractability and ordinary leakage propensity in order to have a more comprehensive view of this phenomenon.

Agents4Pentest, an emerging class of LLM-based autonomous penetration testing systems, has become a rapidly growing area in security research. Despite this growth, the field still lacks a unified taxonomy, a systematic understanding of how agent architectures and evaluation benchmarks have co-evolved, and a clear characterization of remaining capability and reliability gaps. This survey addresses these gaps through a systematic analysis of 81 papers between 2023 and 2026. We organize the literature into six categories: evaluation benchmarks, general-purpose systems, domain-specific frameworks, CTF-based systems, defense-oriented research, and surveys. We further trace a four-phase architectural evolution from text-only reasoning agents to agents trained with Reinforcement Learning with Verifiable Rewards (RLVR), showing that each transition is driven by a distinct capability bottleneck. Our analysis yields several key findings. First, RLVR marks a shift in capability acquisition from imitation of expert demonstrations to reward-driven self-improvement, enabling agents to discover previously undocumented attack strategies. Second, CTF platforms have evolved from evaluation testbeds into dual-purpose infrastructure for both agent evaluation and RL training. Third, domain-specific frameworks improve efficiency through recurring specialization mechanisms, but their gains remain largely confined to narrow task classes and are difficult to compare across domains because existing evaluations rely on different benchmarks. Fourth, the field is expanding beyond offensive automation toward adversarial defense and security compliance. Across these categories, we identify three structurally linked open challenges: evaluation reliability, limited performance on multi-stage attack scenarios, and scarcity of high-quality training data.