Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective 文章

ArXiv CS.AI2026-06-02NEWSen作者: Feng Zhang, Xinhong Ma, Ziqiang Dong, Xi Leng, Jianfei Zhao, Xin Sun, Yang Yang, Guanjun Jiang
查看原文 →
关系图谱

Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective · 相关技术

相关技术

GRPOGroup Relative Policy Optimization