Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published 10 days ago • 54 • 9
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 4 days ago • 46
OmniCap-IF: Benchmarking and Improving Instruction Following Abilities for Omni-Video Captioning Paper • 2606.08572 • Published 4 days ago • 12
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 4 days ago • 46 • 3
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 4 days ago • 46
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published 4 days ago • 46
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills Paper • 2606.07412 • Published 6 days ago • 12
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published 10 days ago • 54 • 9