FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios Paper • 2604.07413 • Published 8 days ago • 91
ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 7 days ago • 255
Watch Before You Answer: Learning from Visually Grounded Post-Training Paper • 2604.05117 • Published 10 days ago • 35
SWE-Next: Scalable Real-World Software Engineering Tasks for Agents Paper • 2603.20691 • Published 26 days ago • 10
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published 29 days ago • 94