Knowledge Distillation During Mid-Training Favors Reasoning over Factual Recall Paper • 2609.01532 • Published 2 days ago • 2
Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents Paper • 2605.29447 • Published May 28 • 21
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 254
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 434