OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published 13 days ago • 749
ReTerm: Recovery Training for Self-Improving Terminal Agents Paper • 2610.18484 • Published 13 days ago • 29
Elephant in the Fridge: Constant-Memory Frame Packing for Long Video Understanding Paper • 2610.16118 • Published 14 days ago • 21
Harness^2: Recursive Agent Harnessing for an Open World Paper • 2610.14224 • Published 17 days ago • 124
AgentSWE: Can Coding Agents Build the Agent You Actually Want? Paper • 2610.13361 • Published 17 days ago • 93
Long-WAM: Scaling the Context of World-Action Models Paper • 2610.10528 • Published 19 days ago • 114