CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization
Abstract
Translating natural language mathematical statements into formal, executable code is a fundamental challenge in automated theorem proving. While prior work has focused on generation and compilation success, little attention has been paid to the critic phase-the evaluation of whether generated formalizations truly capture the semantic intent of the original problem. In this paper, we introduce CriticLean, a novel critic-guided reinforcement learning framework that elevates the role of the critic from a passive validator to an active learning component. Specifically, first, we propose the CriticLeanGPT, trained via supervised fine-tuning and reinforcement learning, to rigorously assess the semantic fidelity of Lean 4 formalizations. Then, we introduce CriticLeanBench, a benchmark designed to measure models' ability to distinguish semantically correct from incorrect formalizations, and demonstrate that our trained CriticLeanGPT models can significantly outperform strong open- and closed-source baselines. Building on the CriticLean framework, we construct FineLeanCorpus, a dataset comprising over 285K problems that exhibits rich domain diversity, broad difficulty coverage, and high correctness based on human evaluation. Overall, our findings highlight that optimizing the critic phase is essential for producing reliable formalizations, and we hope our CriticLean will provide valuable insights for future advances in formal mathematical reasoning.
Cite
@article{arxiv.2507.06181,
title = {CriticLean: Critic-Guided Reinforcement Learning for Mathematical Formalization},
author = {Zhongyuan Peng and Yifan Yao and Kaijing Ma and Shuyue Guo and Yizhe Li and Yichi Zhang and Chenchen Zhang and Yifan Zhang and Zhouliang Yu and Luming Li and Minghao Liu and Yihang Xia and Jiawei Shen and Yuchen Wu and Yixin Cao and Zhaoxiang Zhang and Wenhao Huang and Jiaheng Liu and Ge Zhang},
journal= {arXiv preprint arXiv:2507.06181},
year = {2025}
}