Less is More: Early Stopping Rollout for On-Policy Distillation Paper • 2605.27028 • Published May 26 • 12
Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft Paper • 2604.24697 • Published Apr 27 • 2
Efficient Multi-turn RL for GUI Agents via Decoupled Training and Adaptive Data Curation Paper • 2509.23866 • Published Sep 28, 2025 • 14
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification Paper • 2508.05629 • Published Aug 7, 2025 • 185
