arXiv cs.AI· Yanju Chen, Hanzhi Liu, Ruizhe Qian, Jiaming Shan, Xu Yang, Yufei Ding, Osbert Bastani, Yu Feng·· 56 分钟前AI 评分36
MathEye 框架:通过 Angelic 执行将 LLM 数学证明脚本精炼为完整 Lean 验证证明
From Sorry to QED: Refining LLM Math Proofs via Angelic Execution
AI 导读
论文提出 MathEye 框架,借助 angelic proof checking 将有缺陷的 LLM Lean 证明脚本转化为完全验证的证明:对失败片段插入占位符以隔离待证明义务,再基于证明依赖图做 residual 分析,把义务选择建模为 MaxSAT 优化问题,仅需数学家回答最小必要义务集即可自动重建完整证明。
正文 · 原文
Abstract:Large language models (LLMs) can now generate Lean proof scripts that capture the high-level structure of many mathematical arguments. However, these scripts frequently fail on complex theorems: a single missing side condition or misapplied lemma can cause the prover to abort early and discard an otherwise viable proof outline. This paper presents MathEye, a framework that converts imperfect LLM-generated proof scripts into fully verified Lean proofs by combining symbolic reasoning with minimal human interaction. At the core of MathEye is angelic proof checking, an optimistic execution model that replaces failing proof fragments with placeholders while preserving the overall structure of the argument. This optimistic check produces an angelic proof that isolates the exact proof obligations that the LLM fails to discharge. Because these unresolved obligations are often logically interdependent, asking a mathematician to address every placeholder directly is inefficient. To minimize human effort, MathEye performs residual analysis over a proof dependence graph that captures symbol-level data flow in the angelic proof. By formulating obligation selection as a MaxSAT optimization problem, MathEye selects a minimal-cost set of essential obligations whose resolution suffices to complete the entire proof. MathEye presents these essential obligations to the mathematician in ordinary mathematical language and uses the mathematician's answers to automatically reconstruct the complete Lean proof. Experiments on 30 real-world benchmarks across analysis and algebra show that MathEye solves 93.3% of the problems while reducing the number of required user interactions by 55%.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.22103 [cs.AI] |
| (or arXiv:2611.22103v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22103 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yanju Chen [view email]
[v1]
Tue, 17 Nov 2026 02:39:23 UTC (449 KB)
来源:arXiv cs.AI · arxiv.org