RepoRepair: Leveraging Code Documentation for Repository-Level Automated Program Repair

TL;DR

RepoRepair introduces a novel approach that leverages generated hierarchical code documentation and large language models to improve repository-level program repair, significantly enhancing fault localization and repair success rates.

Contribution

It presents a new documentation-enhanced method using LLMs for global fault localization and repair at the repository level, addressing limitations of existing APR techniques.

Findings

Achieves 45.7% repair rate on SWE-bench Lite

Attains 37.1% repair rate on SWE-bench Multimodal

Demonstrates cost-effective and robust performance across domains

Abstract

Automated program repair (APR) struggles to scale from isolated functions to full repositories, as it demands a global, task-aware understanding to locate necessary changes. Current methods, limited by context and reliant on shallow retrieval or costly agent iterations, falter on complex cross-file issues. To this end, we propose RepoRepair, a novel documentation-enhanced approach for repository-level fault localization and program repair. Our core insight is to leverage LLMs to generate hierarchical code documentation (from functions to files) for code repositories, creating structured semantic abstractions that enable LLMs to comprehend repository-level context and dependencies. Specifically, RepoRepair first employs a text-based LLM (e.g., DeepSeek-V3) to generate file/function-level code documentation for repositories, which serves as auxiliary knowledge to guide fault localization. Subsequently, based on the fault localization results and the issue description, a powerful LLM (e.g., Claude-4) attempts to repair the identified suspicious code snippets. Evaluated on SWE-bench Lite, RepoRepair achieves a 45.7% repair rate at a low cost of $0.44 per fix. On SWE-bench Multimodal, it delivers state-of-the-art performance with a 37.1% repair rate despite a higher cost of $0.56 per fix, demonstrating robust and cost-effective performance across diverse problem domains.