{"ID":2889899,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.20199","arxiv_id":"2507.20199","title":"StepFun-Prover Preview: Let's Think and Verify Step by Step","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 $70.0\\%$. 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.","short_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 approac...","url_abs":"https://arxiv.org/abs/2507.20199","url_pdf":"https://arxiv.org/pdf/2507.20199v3","authors":"[\"Shijie Shang\",\"Ruosi Wan\",\"Yue Peng\",\"Yutong Wu\",\"Xiong-hui Chen\",\"Jie Yan\",\"Xiangyu Zhang\"]","published":"2025-07-27T09:38:32Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Language Model\"]","has_code":false}