Multi-Rollout On-Policy Distillation via Peer Successes and Failures 文章

ArXiv CS.AI2026-06-02NEWSen作者: Weichen Yu, Xiaomin Li, Yizhou Zhao, Xiaoze Liu, Ruowang Zhang, Haixin Wang, Yinyi Luo, Chen Henry Wu, Gaurav Mittal, Matt Fredrikson, Yu Hu

Multi-Rollout On-Policy Distillation via Peer Successes and Failures · 相关技术