Socratic Skill Learning: Interleaving Teaching and Practice for Transferable Agent Skills Paper • 2610.17860 • Published 17 days ago • 51
ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory Paper • 2607.10350 • Published Jul 15 • 80
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published Jun 7 • 53
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published Jun 1 • 59