RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time Paper • 2604.11626 • Published 8 days ago • 100
FORGE:Fine-grained Multimodal Evaluation for Manufacturing Scenarios Paper • 2604.07413 • Published 13 days ago • 94
ClawBench: Can AI Agents Complete Everyday Online Tasks? Paper • 2604.08523 • Published 12 days ago • 256
Watch Before You Answer: Learning from Visually Grounded Post-Training Paper • 2604.05117 • Published 15 days ago • 35
SWE-Next: Scalable Real-World Software Engineering Tasks for Agents Paper • 2603.20691 • Published Mar 21 • 10
OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis Paper • 2603.20278 • Published Mar 17 • 95