ActiveSaddler: Automated Curriculum Learning for Agent Harness Optimization Paper • 2610.00906 • Published Oct 1 • 60
Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States Paper • 2610.01415 • Published Oct 1 • 65
WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents Paper • 2609.40325 • Published Sep 30 • 80
EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific Discovery Paper • 2609.40340 • Published Sep 30 • 112
AREX-2: Advancing Self-Improving Agents through Long-Horizon Reflective Tasks Paper • 2609.38288 • Published Sep 29 • 117
OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction Paper • 2610.01762 • Published Oct 1 • 80
Keep It InMind: Benchmarking the Implicit-Association Blind Spot in Agent Memory Paper • 2607.24368 • Published Jul 27 • 31
Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model Paper • 2607.24904 • Published Jul 27 • 39
Beacon: Knowing When and How to Perform Agentic Visual Reasoning Paper • 2607.28595 • Published Jul 30 • 56
Running on Zero Agents Featured 110 Mage-VL 🎞 110 Codec-native video & image understanding with Mage-VL 4B
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published Jul 19 • 91
JarvisHub: An Open Harness for Canvas-Native Multimodal Creative Agents Paper • 2607.23588 • Published Jul 26 • 87
GNM Head: A Generative aNthropometric Model of the human head Paper • 2607.23687 • Published Jul 26 • 7