Lean-Auto: An Interface Between Lean 4 and Automated Theorem Provers
Yicheng Qian, Joshua Clune, Clark W. Barrett, Jeremy Avigad
Abstract
Abstract Proof automation is crucial to large-scale formal mathematics and software/hardware verification projects in ITPs. Sophisticated tools called hammers have been developed to provide general-purpose proof automation in ITPs such as Coq and Isabelle, leveraging the power of ATPs. An important component of a hammer is the translation algorithm from the ITP’s logical system to the ATP’s logical system. In this paper, we propose a novel translation algorithm for ITPs based on dependent type theory. The algorithm is implemented in Lean 4 under the name Lean-auto. When combined with ATPs, Lean-auto provides general-purpose, ATP-based proof automation in Lean 4 for the first time. Soundness of the main translation procedure is guaranteed, and experimental results suggest that our algorithm is sufficiently complete to automate the proof of many problems that arise in practical uses of Lean 4. We also find that Lean-auto solves more problems than existing tools on Lean 4’s math library Mathlib4.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext 3265eae6-e63c-41f6-82c2-c3c89e98261fCited by top-tier papers2
- Premise Selection for a Lean HammerThomas Zhu, Joshua Clune, Jeremy Avigad, Albert Q. Jiang et al.ICLR 2026 · 13 citations
- Foundational Multi-Modal Program VerifiersVladimir Gladshtein, George Pîrlea, Qiyuan Zhao, Vitaly Kurin et al.POPL 2026 · 4 citations
Builds on1
Related papers
- ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint EmbeddingsPrithwish Jana, Kaan Kale, Ahmet Ege Tanriverdi, Cruise Song et al.ICLR 2026 · 19 citations
- Neuro-Symbolic Proof Generation for Scaling Systems Software VerificationBaoding He, Zenan Li, Wei Sun, Yuan Yao et al.OSDI 2026
- Herald: A Natural Language Annotated Lean 4 DatasetGuoxiong Gao, Yutong Wang, Jiedong Jiang, Qi Gao et al.ICLR 2025
- TacticZero: Learning to Prove Theorems from Scratch with Deep Reinforcement LearningMinchao Wu, Michael Norrish, Christian Walder, Amir DezfouliNeurIPS 2021 · 56 citations
- Lean Finder: Semantic Search for Mathlib That Understands User IntentsJialin Lu, Kye Emond, Kaiyu Yang, Swarat Chaudhuri et al.ICLR 2026 · 10 citations
