Reproducing, Analyzing, and Detecting Reward Hacking in Rubric-Based Reinforcement Learning Paper • 2606.04923 • Published 2 days ago • 34
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published 8 days ago • 186
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 9 days ago • 419