Saved in:
Bibliographic Details
Main Authors: Xin, Huajian, Li, Luming, Jin, Xiaoran, Fleuriot, Jacques, Li, Wenda
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2504.19110
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910007996448768
author Xin, Huajian
Li, Luming
Jin, Xiaoran
Fleuriot, Jacques
Li, Wenda
author_facet Xin, Huajian
Li, Luming
Jin, Xiaoran
Fleuriot, Jacques
Li, Wenda
contents While frontier formal mathematics systems now routinely develop repository-scale proof engineering artifacts requiring multi-file coordination and semantic correctness beyond compilation, existing evaluation benchmarks remain focused on isolated theorem proving. We introduce Automated Proof Engineering (APE), the first systematic framework for evaluating repository-scale proof engineering through dual verification that validates both syntactic compilation and semantic requirement satisfaction in pinned library environments. We present a complete infrastructure comprising APE-Bench, which automatically extracts proof engineering tasks from real library commit histories, and APE-Harness, a unified execution framework based on task contract abstraction. This contract-based design enables standardized evaluation across diverse formal mathematics tasks and fair systematic comparison of different agent implementations (including our APE-Agent reference scaffold alongside Claude Code and Codex CLI) on identical task specifications. We demonstrate the framework's effectiveness through comprehensive evaluation. All code and benchmark dataset are released as open-source at https://github.com/xinhjBrant/APE-Bench.
format Preprint
id arxiv_https___arxiv_org_abs_2504_19110
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle APE-Bench: Evaluating Automated Proof Engineering for Formal Math Libraries
Xin, Huajian
Li, Luming
Jin, Xiaoran
Fleuriot, Jacques
Li, Wenda
Computation and Language
While frontier formal mathematics systems now routinely develop repository-scale proof engineering artifacts requiring multi-file coordination and semantic correctness beyond compilation, existing evaluation benchmarks remain focused on isolated theorem proving. We introduce Automated Proof Engineering (APE), the first systematic framework for evaluating repository-scale proof engineering through dual verification that validates both syntactic compilation and semantic requirement satisfaction in pinned library environments. We present a complete infrastructure comprising APE-Bench, which automatically extracts proof engineering tasks from real library commit histories, and APE-Harness, a unified execution framework based on task contract abstraction. This contract-based design enables standardized evaluation across diverse formal mathematics tasks and fair systematic comparison of different agent implementations (including our APE-Agent reference scaffold alongside Claude Code and Codex CLI) on identical task specifications. We demonstrate the framework's effectiveness through comprehensive evaluation. All code and benchmark dataset are released as open-source at https://github.com/xinhjBrant/APE-Bench.
title APE-Bench: Evaluating Automated Proof Engineering for Formal Math Libraries
topic Computation and Language
url https://arxiv.org/abs/2504.19110