cs.AINov 17, 2026

From Sorry to QED: Refining LLM Math Proofs via Angelic Execution

Authors: Yanju Chen, Hanzhi Liu, Ruizhe Qian, Jiaming Shan, Xu Yang, Yufei Ding, Osbert Bastani, Yu Feng

Organizations: Department of Computer Science and Engineering, University of California, San Diego, La Jolla, CA 92093, USA · Department of Computer Science, University of California, Santa Barbara, Santa Barbara, CA 93106, USA · Department of Mathematics, Pennsylvania State University, University Park, PA 16802, USA · Department of Mathematics, University of California, Santa Barbara, Santa Barbara, CA 93106, USA · 

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%.

Figures & tables

Explore similar work

Apr 7, 2026

ProofSketcher: Hybrid LLM + Lightweight Proof Checker for Reliable Math/Logic Reasoning

The large language models (LLMs) might produce a persuasive argument within mathematical and logical fields, although such argument often includes some minor missteps, including the entire omission of side conditions, invalid inference patterns, or appeals to a lemma that cannot be derived logically out of the context being discussed. These omissions are infamously hard to notice solely out of the text, as even the misconstrued construction still may seem mostly accurate. Conversely, interactive theorem provers like Lean and Coq have rigorous reliability by ensuring that syntactic and semantic statements only accept statements that can pass all the syntactic and semantic steps in the program which is a small trusted kernel of the language type-checks with. Despite the fact that this technique provides strong guarantees, it comes at quite a heavy price: the evidence must be completely formalized, and the evidence user or a auxiliary search program must provide an avalanche of low-level information. This paper presents a hybrid pipeline where an LLM generates a typed proof sketch in a compact DSL and a lightweight trusted kernel expands the sketch into explicit proof obligations.
Jun 4, 2026

Evaluation of LLMs for Mathematical Formalization in Lean

Within the past few years, the ability of Large Language Models (LLMs) to generate formal mathematical proofs has improved drastically. We provide a comparison of various LLMs' effectiveness in producing formal proofs in Lean 4 with the goal of assisting those seeking to use LLMs to support their own projects. We utilize both pass@kk and refine@kk metrics as the benchmark for our comparison and evaluate on subsets of both miniF2F and miniCTX datasets. Our testing shows that overall, Gemini 3.1 Pro and Claude Opus 4.7 perform best. Gemini 3.1 Pro achieved a 92% success rate on miniF2F via refine@32 whereas Opus 4.7 achieved a 86% success rate on miniCTX via refine@32. When taking cost into account, NVIDIA Nemotron 3 Super and GPT-OSS 120B were the most efficient, with competitive accuracies and average costs of <\0.01$ per correct proof.
Jun 13, 2026

Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs

Large language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level reasoning in long proofs across diverse sources. This evaluation gap limits trustworthy AI assistance in proof-certified scientific progress. Existing evaluations often emphasize final answers or rely on costly expert grading, while end-to-end proof generation remains open-ended and hard to verify automatically. We introduce Mask-Proof, a pipeline that turns real proofs into automatically checkable masked-step tasks. It masks key formula steps, provides the necessary surrounding context, and evaluates model reconstructions with an LLM-based equivalence judge using repeated votes for stability. The resulting Mask-ProofBench contains 292 curated problems across diverse research areas. Experiments with 17 models show that reasoning-enhanced models outperform standard models by 12% to 27%. Our evaluator achieves 96.8% agreement with expert annotators, enabling faithful, reproducible, and comparable measurement of step-level mathematical reasoning. Benchmark, annotations, and code are available at https://github.com/weating/Mask-Proof.