GuoLiangTang

Tommy930's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted 3 papers about 2 hours ago

Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability Composition

Paper • 2610.28578 • Published 1 day ago • 43

HERA: Harness-Environment Co-Evolution for Reliable Agentic Abstention

Paper • 2610.06563 • Published 16 days ago • 4

Evidence-First Agentic Verification

Paper • 2610.17724 • Published 8 days ago • 17

upvoted 8 papers about 16 hours ago

BlenderWorld: Benchmarking Visual Agents for 3D Creation from Real-World References

Paper • 2610.23986 • Published 7 days ago • 22

HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

Paper • 2610.26770 • Published 2 days ago • 27

MemPilot: Orchestrating On-Demand Multimodal Memory Curation for LLM Agents

Paper • 2610.06830 • Published 16 days ago • 26

Interlock: From Local Correctness to Task Completion in Long-Horizon Agents

Paper • 2610.19686 • Published 7 days ago • 34

Self-Evolving Coding Agents via Harness-Policy Optimization

Paper • 2610.22791 • Published 5 days ago • 45

MemT-1.0: Towards Memory-Native Evolution

Paper • 2610.26825 • Published 2 days ago • 146

OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal Memory

Paper • 2610.26860 • Published 2 days ago • 99

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 6 days ago • 427

upvoted 9 papers 2 days ago

Into the Unknown: Benchmarking AI agents on open scientific research problems

Paper • 2610.19159 • Published 8 days ago • 147

LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving Markets

Paper • 2610.09872 • Published 14 days ago • 119

Xiaomi-Lens-0 Technical Report

Paper • 2610.23279 • Published 5 days ago • 35

LEV: Thinking Fast and Deep with Looped Decision Models

Paper • 2610.20951 • Published 7 days ago • 494

FC-SWE: Failure-Conditioned RL for Long-Horizon Software Engineering Agents

Paper • 2610.07898 • Published 15 days ago • 6

Towards Looped Models Done Right, Part I: Topology, Input Injection, Recurrent-State Design

Paper • 2610.23036 • Published 5 days ago • 12

Can Visual Generation Expand What Unified Multimodal Models Know?

Paper • 2610.21459 • Published 6 days ago • 26

MOSS-Image Technical Report

Paper • 2610.23374 • Published 5 days ago • 75

DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses

Paper • 2610.23839 • Published 5 days ago • 17