CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents Paper • 2606.22883 • Published 27 days ago • 37
CoVEBench: Can Video Editing Models Handle Complex Instructions? Paper • 2606.08415 • Published Jun 7 • 52
Where Do Deep-Research Agents Go Wrong? Span-Level Error Localization in Agent Trajectories Paper • 2606.02060 • Published Jun 1 • 58