MAI-Gym: An Open All-in-One Platform for GUI Agent Evaluation and RL Training across Mobile and Computer Environments Paper • 2610.20939 • Published 5 days ago • 155
OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding Paper • 2610.18829 • Published 6 days ago • 579
Raven: The Harness of Harnesses for Composable Agentic Intelligence Paper • 2609.33439 • Published 22 days ago • 676