English

StepFun-Prover Preview: Let's Think and Verify Step by Step

Artificial Intelligence 2025-08-14 v3

Abstract

We present StepFun-Prover Preview, a large language model designed for formal theorem proving through tool-integrated reasoning. Using a reinforcement learning pipeline that incorporates tool-based interactions, StepFun-Prover can achieve strong performance in generating Lean 4 proofs with minimal sampling. Our approach enables the model to emulate human-like problem-solving strategies by iteratively refining proofs based on real-time environment feedback. On the miniF2F-test benchmark, StepFun-Prover achieves a pass@1 success rate of 70.0%70.0\%. Beyond advancing benchmark performance, we introduce an end-to-end training framework for developing tool-integrated reasoning models, offering a promising direction for automated theorem proving and Math AI assistant.

Keywords

Cite

@article{arxiv.2507.20199,
  title  = {StepFun-Prover Preview: Let's Think and Verify Step by Step},
  author = {Shijie Shang and Ruosi Wan and Yue Peng and Yutong Wu and Xiong-hui Chen and Jie Yan and Xiangyu Zhang},
  journal= {arXiv preprint arXiv:2507.20199},
  year   = {2025}
}

Comments

Added links to GitHub and Hugging Face

R2 v1 2026-07-01T04:20:48.528Z