Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yang, Haotong, Wang, Zitong, Kang, Shijia, Yang, Siqi, Yu, Wenkai, Niu, Xu, Sun, Yike, Hu, Yi, Lin, Zhouchen, Zhang, Muhan
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2602.02377
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866911457239629824
author Yang, Haotong
Wang, Zitong
Kang, Shijia
Yang, Siqi
Yu, Wenkai
Niu, Xu
Sun, Yike
Hu, Yi
Lin, Zhouchen
Zhang, Muhan
author_facet Yang, Haotong
Wang, Zitong
Kang, Shijia
Yang, Siqi
Yu, Wenkai
Niu, Xu
Sun, Yike
Hu, Yi
Lin, Zhouchen
Zhang, Muhan
contents While Large Language Models (LLMs) have demonstrated strong math reasoning abilities through Reinforcement Learning with *Verifiable Rewards* (RLVR), many advanced mathematical problems are proof-based, with no guaranteed way to determine the authenticity of a proof by simple answer matching. To enable automatic verification, a Reward Model (RM) capable of reliably evaluating full proof processes is required. In this work, we design a *scalable* data-construction pipeline that, with minimal human effort, leverages LLMs to generate a large quantity of high-quality ``**question-proof-check**'' triplet data. By systematically varying problem sources, generation methods, and model configurations, we create diverse problem-proof pairs spanning multiple difficulty levels, linguistic styles, and error types, subsequently filtered through hierarchical human review for label alignment. Utilizing these data, we train a proof-checking RM, incorporating an ``LLM-as-a-RM-for-RM'' approach and balanced token weighting to stabilize the RL process. Our experiments validate the model's scalability and strong performance from multiple perspectives, including reward accuracy, generalization ability and test-time guidance, providing important practical recipes and tools for strengthening LLM mathematical capabilities.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02377
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Proof-RM: A Scalable and Generalizable Reward Model for Math Proof
Yang, Haotong
Wang, Zitong
Kang, Shijia
Yang, Siqi
Yu, Wenkai
Niu, Xu
Sun, Yike
Hu, Yi
Lin, Zhouchen
Zhang, Muhan
Computation and Language
While Large Language Models (LLMs) have demonstrated strong math reasoning abilities through Reinforcement Learning with *Verifiable Rewards* (RLVR), many advanced mathematical problems are proof-based, with no guaranteed way to determine the authenticity of a proof by simple answer matching. To enable automatic verification, a Reward Model (RM) capable of reliably evaluating full proof processes is required. In this work, we design a *scalable* data-construction pipeline that, with minimal human effort, leverages LLMs to generate a large quantity of high-quality ``**question-proof-check**'' triplet data. By systematically varying problem sources, generation methods, and model configurations, we create diverse problem-proof pairs spanning multiple difficulty levels, linguistic styles, and error types, subsequently filtered through hierarchical human review for label alignment. Utilizing these data, we train a proof-checking RM, incorporating an ``LLM-as-a-RM-for-RM'' approach and balanced token weighting to stabilize the RL process. Our experiments validate the model's scalability and strong performance from multiple perspectives, including reward accuracy, generalization ability and test-time guidance, providing important practical recipes and tools for strengthening LLM mathematical capabilities.
title Proof-RM: A Scalable and Generalizable Reward Model for Math Proof
topic Computation and Language
url https://arxiv.org/abs/2602.02377