DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xie, Xuan, Wang, Xuan, Wang, Wenjie, Chen, Shuai, Lin, Wei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!