EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Chengjun, Liu, Shichun, Lin, Jiahang, Zhu, Dingwei, Zhang, Jiazheng, Dou, Shihan, Gao, Songyang, Han, Zhenhua, Wang, Binghai, Zheng, Rui, Huang, Xuanjing, Gui, Tao, Feng, Yansong
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!