ICPO: Intrinsic Confidence-Driven Group Relative Preference Optimization for Efficient Reinforcement Learning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Jinpeng, Li, Chao, Ye, Ting, Zhang, Mengyuan, Liu, Wei, Luan, Jian
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Information Retrieval
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2511.21005