ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 2 days ago • 83
Watch Before You Answer: Learning from Visually Grounded Post-Training Paper • 2604.05117 • Published 5 days ago • 30
ImagenWorld: Stress-Testing Image Generation Models with Explainable Human Evaluation on Open-ended Real-World Tasks Paper • 2603.27862 • Published 12 days ago • 30
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 24 days ago • 94
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 24 days ago • 94
OpenResearcher Collection OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis • 8 items • Updated 18 days ago • 17
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 24 days ago • 94