OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published 14 days ago • 749
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 19 days ago • 245
Incremental Open-Ended Deep Research with Structured Harness Paper • 2610.11566 • Published 19 days ago • 8
World Editing: Intervening on Executable Worlds at Increasing Depth Paper • 2610.02331 • Published 26 days ago • 31
Self-Supervised Scaling of Terminal Environments for Scientific Domains Paper • 2610.02710 • Published 25 days ago • 14
Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents Paper • 2609.17653 • Published Sep 15 • 45
Adaptive Bridge: A Proxy-Based Decoupling Layer for Mitigating DDS Backpressure in ROS 2 Paper • 2608.15380 • Published Sep 6 • 24