HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published Oct 2 • 22
HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing Agents Paper • 2610.03574 • Published Oct 2 • 22
Ego2Act: Evaluating Goal-Directed Manipulation in Egocentric Video Generation Paper • 2610.01092 • Published Oct 1 • 20
PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialogues Paper • 2601.17277 • Published Jan 24 • 6