Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published 11 days ago • 54 • 9
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 5 days ago • 47
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning Paper • 2606.08572 • Published 5 days ago • 13
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 5 days ago • 47 • 3
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 5 days ago • 47
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 5 days ago • 47
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills Paper • 2606.07412 • Published 7 days ago • 12
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published 11 days ago • 54 • 9