OpenProver: Agentic and Interactive Theorem Proving with Lean 4
Quick Answer
OpenProver is an open-source LLM-driven automated theorem proving system utilizing Lean 4, featuring a Planner-Worker-Verifier architecture.
Quick Take
OpenProver is an open-source LLM-driven automated theorem proving system utilizing Lean 4, featuring a Planner-Worker-Verifier architecture. It offers interactive proof search capabilities and automatic formal verification, allowing users to monitor and guide the theorem proving process effectively. The system is publicly available and evaluated against ProofNet, demonstrating its potential for quantitative ablation experiments.
Key Points
- OpenProver integrates a Planner-Worker-Verifier architecture for efficient theorem proving.
- The system allows human operators to interactively guide the proof search process.
- OpenProver is fully open-source and enables reproducible evaluations through formal verification.
- It was evaluated on ProofNet, showcasing its capabilities in quantitative experiments.
- The project is publicly available, promoting collaboration and further research.
Paper Resources
📖 Reader Mode
~2 min readAbstract:In this system paper, we present OpenProver, an open-source system for LLM-driven automated theorem proving (ATP) with integrated Lean 4 formal verification. OpenProver integrates a Planner-Worker-Verifier architecture inspired by recent ATP agentic systems such as Aletheia. A Planner agent maintains a compact Whiteboard scratchpad and an unbounded Repository of intermediate findings, and decomposes mathematical work into parallel Workers.
OpenProver is fully open-source, offers reproducible evaluation through automatic formal verification of generated proofs, and provides an interactive terminal interface for human-guided proof search. In interactive mode, OpenProver allows the human operator to monitor and steer the proof search process, motivated by the established human-AI synergy in interactive code generation.
To showcase the potential for quantitative ablation experiments enabled by automatic formal verification, we evaluate OpenProver on ProofNet and compare it with a simple baseline. OpenProver is publicly available at this https URL.
| Comments: | 7 pages, 2 figures. Accepted at the 19th Conference on Intelligent Computer Mathematics (CICM 2026) |
| Subjects: | Artificial Intelligence (cs.AI); Mathematical Software (cs.MS) |
| Cite as: | arXiv:2607.09217 [cs.AI] |
| (or arXiv:2607.09217v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.09217 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Matěj Kripner [view email]
[v1]
Fri, 10 Jul 2026 09:07:12 UTC (81 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →Adversarial Social Epistemology for Assemblies of Humans and Large Language Models
The paper introduces Adversarial Social Epistemology (ASE) to analyze how agents manipulate trust in public communications, highlighting mechanisms that undermine the reliability of testimony and inference. It critiques existing frameworks like epistemic bubbles and misinformation diffusion, proposing a new language for understanding trust breaches and auditing inferential chains in densely interactive environments involving humans and large language models.