arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2506.22005cs.AI
收藏

LeanConjecturer:用于定理证明的数学猜想自动生成

LeanConjecturer: Automatic Generation of Mathematical Conjectures for Theorem Proving

OMRON SINIC X Corporation(OMRON SINIC X公司);Department of Physics, Kyoto University(京都大学物理系);AI Innovation Research Promotion Center, Shiga University(Shiga大学AI创新研究促进中心);Research and Development Center for Large Language Models, National Institute of Informatics(国家信息研究所大型语言模型研究开发中心);National Institute of Science and Technology Policy (NISTEP)(科学技术政策研究所)

Naoto Onda, Kazumi Kasaura, Yuta Oriike, Masaya Taniguchi, Akiyoshi Sannai, Sho Sonoda

AI总结:

本文提出LeanConjecturer流水线,结合规则与LLM在Lean 4中自动生成数学猜想,并利用GRPO强化学习增强定理证明能力,为定理证明系统提供可扩展的训练数据生成方案。

摘要:

我们介绍了LeanConjecturer,这是一个使用大型语言模型(LLMs)在Lean 4中自动生成大学水平数学猜想的流水线。我们的混合方法将基于规则的上下文提取与基于LLM的定理陈述生成相结合,解决了形式化定理证明中的数据稀缺挑战。通过迭代生成和评估,LeanConjecturer从40个Mathlib种子文件中产生了12,289个猜想,其中3,776个被确定为语法有效且非平凡的,即无法通过\ exttt{aesop}策略证明。我们通过组相对策略优化(GRPO)展示了这些生成的猜想在强化学习中的实用性,表明在特定领域的猜想上进行针对性训练可以增强定理证明能力。我们的方法平均每个种子文件生成103.25个新猜想,为定理证明系统创建训练数据提供了可扩展的解决方案。我们的系统成功验证了拓扑学中的几个非平凡定理,包括半开集、alpha开集和预开集的性质,展示了其在超越现有结果的简单变体之外进行数学发现的潜力。

英文摘要:

We introduce LeanConjecturer, a pipeline for automatically generating university-level mathematical conjectures in Lean 4 using Large Language Models (LLMs). Our hybrid approach combines rule-based context extraction with LLM-based theorem statement generation, addressing the data scarcity challenge in formal theorem proving. Through iterative generation and evaluation, LeanConjecturer produced 12,289 conjectures from 40 Mathlib seed files, with 3,776 identified as syntactically valid and non-trivial, that is, cannot be proven by \texttt{aesop} tactic. We demonstrate the utility of these generated conjectures for reinforcement learning through Group Relative Policy Optimization (GRPO), showing that targeted training on domain-specific conjectures can enhance theorem proving capabilities. Our approach generates 103.25 novel conjectures per seed file on average, providing a scalable solution for creating training data for theorem proving systems. Our system successfully verified several non-trivial theorems in topology, including properties of semi-open, alpha-open, and pre-open sets, demonstrating its potential for mathematical discovery beyond simple variations of existing results.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑