WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization for Rollout-Efficient Reasoning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mundada, Gagan, Huang, Zihan, Surana, Rohan, Yu, Sheldon, Zhang, Jennifer Yuntong, Li, Xintong, Yu, Tong, Yao, Lina, Shang, Jingbo, McAuley, Julian, Wu, Junda
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!