Saved in:
Bibliographic Details
Main Authors: Yang, Haotong, Wang, Zitong, Kang, Shijia, Yang, Siqi, Yu, Wenkai, Niu, Xu, Sun, Yike, Hu, Yi, Lin, Zhouchen, Zhang, Muhan
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.02377
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of 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.