arXiv cs.AI· Ruida Wang, Jerry Huang, Pengcheng Wang, Xuanqing Liu, Luyang Kong, Tong Zhang·· 13 小时前AI 评分39
Lean4Agent：用 Lean4 对智能体工作流与轨迹进行形式化建模与验证
Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory
AI 导读
Lean4Agent 是首个用依赖类型形式语言 Lean4 建模并验证智能体行为的框架，包含可扩展的 Lean4 库 FormalAgentLib 和基于其修正工作流的 LeanEvolve。
正文 · 原文
Abstract:Equipping Large Language Models (LLMs) to execute reliable multi-step workflows has become a central challenge in artificial intelligence. Despite recent advances in LLMs' agentic capabilities, most agent systems still lack formal methods for specifying, verifying, and debugging their workflow and execution trajectories. This challenge mirrors a long-standing problem in mathematics, where the ambiguity of natural languages (NLs) motivates the development of formal languages (FLs). Inspired by this paradigm, we propose **Lean4Agent**, to the best of our knowledge, the first framework that uses Lean4, a dependent-type FL to model and verify agent behavior. **Lean4Agent** launches **FormalAgentLib**, an extensible Lean4 library for formally modeling and verifying agent workflows' semantic consistency under explicit assumptions, and enabling localization of execution-time failures revealed by trajectories. Building on **FormalAgentLib**, we further develop **LeanEvolve**, which applies results in **FormalAgentLib** to revise workflows to enhance its capability. Extensive experiments on a hard problem subset of SWE-Bench-Verified and a subset of ELAIP-Bench across 5 leading LLMs indicate that the verification-passing workflows outperform the failing ones by an average of **11.94%**, and **LeanEvolve** further improves SWE performance by **7.47%** on average. Furthermore, **Lean4Agent** establishes a foundation for a new field of using expressive dependent-type FL to formally model and verify agent behavior.
| Comments: | Nips 2026 accepted paper |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Logic in Computer Science (cs.LO); Software Engineering (cs.SE) |
| Cite as: | arXiv:2606.06523 [cs.AI] |
| (or arXiv:2606.06523v3 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.06523 arXiv-issued DOI via DataCite |
Submission history
From: Ruida Wang [view email]
[v1]
Tue, 2 Jun 2026 18:46:50 UTC (542 KB)
[v2]
Mon, 15 Jun 2026 18:24:02 UTC (542 KB)
[v3]
Tue, 20 Oct 2026 22:43:41 UTC (525 KB)
来源：arXiv cs.AI · arxiv.org