RePO: Bridging On-Policy Learning and Off-Policy Knowledge through Rephrasing Policy Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xia, Linxuan, Yang, Xiaolong, Chen, Yongyuan, Zhao, Enyue, Cai, Deng, Wang, Yasheng, Wu, Boxi
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!