AVSCap: Orchestrating Audio-Visual Synergy for Omni-modal Video Captioning Paper • 2607.12820 • Published Jul 14 • 3
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published Jun 1 • 59
MMG2Skill: Can Agents Distill In-the-Wild Guides into Self-Evolving Skills? Paper • 2606.01993 • Published Jun 1 • 17