Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification 文章

ArXiv CS.AI2026-06-02NEWSen作者: Shihao Ji, Haotao Tan, Zihui Song, Mingyu Li
查看原文 →
关系图谱

Expected Value Alignment for Generative Reward Modeling in Formal Mathematics Verification · 相关技术

相关技术

Expected Value Alignmentgenerative reward modelsValue-head modelsprocess reward modelsearch methodsreinforcement learninglarge language models