Watch and Learn: Learning to Use Computers from Online Videos Paper • 2510.04673 • Published Oct 6 • 11
SpaceTools: Tool-Augmented Spatial Reasoning via Double Interactive RL Paper • 2512.04069 • Published 14 days ago • 21
An Illusion of Progress? Assessing the Current State of Web Agents Paper • 2504.01382 • Published Apr 2 • 4
Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge Paper • 2506.21506 • Published Jun 26 • 51