Proof-RM: A Scalable and Generalizable Reward Model for Math Proof

• URL: http://arxiv.org/abs/2602.02377v1
• Date: Mon, 02 Feb 2026 17:42:53 GMT
• Title: Proof-RM: A Scalable and Generalizable Reward Model for Math Proof
• Authors: Haotong Yang, Zitong Wang, Shijia Kang, Siqi Yang, Wenkai Yu, Xu Niu, Yike Sun, Yi Hu, Zhouchen Lin, Muhan Zhang,
• Abstract summary: Large Language Models (LLMs) have demonstrated strong math reasoning abilities through Reinforcement Learning with *Verifiable Rewards* (RLVR)<n>Many advanced mathematical problems are proof-based, with no guaranteed way to determine the authenticity of a proof by simple answer matching.<n>To enable automatic verification, a Reward Model (RM) capable of reliably evaluating full proof processes is required.
• Score: 67.53066972145183
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 additional process reward and token weight balance 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.

Related papers

• CoSineVerifier: Tool-Augmented Answer Verification for Computation-Oriented Scientific Questions [32.14674040685995]
  We introduce model, a tool-augmented verifier that leverages external rubrics to perform precise computations and symbolic simplifications.<n>Experiments conducted on STEM subjects, general QA, and long-form reasoning tasks demonstrates strong generalization of model.
  arXiv  Detail & Related papers  (2025-12-01T03:08:43Z)
• From Answers to Rationales: Self-Aligning Multimodal Reasoning with Answer-Oriented Chain-of-Thought [43.07899102255169]
  Current methods primarily focus on positive rationales, typically relying on manual annotations or complex systems.<n>We propose a novel framework: textbfSelf-Aligning textbfMultimodal Reasoning with textbfAnswertextbfriented Chain-of-textbfThought.
  arXiv  Detail & Related papers  (2025-07-01T08:24:51Z)
• Towards Reliable Proof Generation with LLMs: A Neuro-Symbolic Approach [14.213719696233934]
  Large language models (LLMs) struggle with formal domains that require rigorous logical deduction and symbolic reasoning.<n>We propose a neuro-symbolic approach that combines LLMs' generative strengths with structured components to overcome this challenge.
  arXiv  Detail & Related papers  (2025-05-20T15:13:32Z)
• Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation [69.62857948698436]
  Recent advances in large language models (LLMs) have improved their performance on coding benchmarks.<n>However, improvement is plateauing due to the exhaustion of readily available high-quality data.<n>We propose Sol-Ver, a self-play solver-verifier framework that jointly improves a single model's code and test generation capacity.
  arXiv  Detail & Related papers  (2025-02-20T18:32:19Z)
• MathGAP: Out-of-Distribution Evaluation on Problems with Arbitrarily Complex Proofs [80.96119560172224]
  MathGAP generates problem statements and chain-of-thought reasoning traces according to specifications about their arithmetic proof structure.<n>Using MathGAP, we find that LLMs show a significant decrease in performance as proofs get deeper and wider.
  arXiv  Detail & Related papers  (2024-10-17T12:48:14Z)
• Improving LLM Reasoning through Scaling Inference Computation with Collaborative Verification [52.095460362197336]
  Large language models (LLMs) struggle with consistent and accurate reasoning. LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors. We propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification.
  arXiv  Detail & Related papers  (2024-10-05T05:21:48Z)
• SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models [54.78329741186446]
  We propose a novel paradigm that uses a code-based critic model to guide steps including question-code data construction, quality control, and complementary evaluation. Experiments across both in-domain and out-of-domain benchmarks in English and Chinese demonstrate the effectiveness of the proposed paradigm.
  arXiv  Detail & Related papers  (2024-08-28T06:33:03Z)
• MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data [85.50740598523818]
  MUSTARD is a framework that masters uniform synthesis of theorem and proof data of high quality and diversity. We present a theorem-and-proof benchmark MUSTARDSAUCE with 5,866 valid data points. We perform extensive analysis and demonstrate that MUSTARD generates validated high-quality step-by-step data.
  arXiv  Detail & Related papers  (2024-02-14T05:57:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.