False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents Paper • 2609.39102 • Published Sep 30 • 150
view article Article autotrust/JEV-27B: fast, calibrated decisions and full reasoning from one open model autotrust • Sep 27 • 26
Annotations as Rollouts: Efficient and Scalable Reinforcement Learning for Video MLLMs Paper • 2608.20492 • Published Aug 20 • 40