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

arXiv: https://arxiv.org/abs/2603.01048 · HTML: https://mlsanity.com/paper/2603.01048/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 50 references that are in the map.
- First posted on arXiv 1 Mar 2026.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Competition-Level Code Generation with AlphaCode](https://mlsanity.com/paper/2203.07814/) (2022)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Unsupervised Translation of Programming Languages](https://mlsanity.com/paper/2006.03511/) (2020)
- [RepairAgent: An Autonomous, LLM-Based Agent for Program Repair](https://mlsanity.com/paper/2403.17134/) (2024)
- [SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?](https://mlsanity.com/paper/2410.03859/) (2024)
- [SWE-Search: Enhancing Software Agents with Monte Carlo Tree Search and Iterative Refinement](https://mlsanity.com/paper/2410.20285/) (2024)
- [A Convolutional Attention Network for Extreme Summarization of Source Code](https://mlsanity.com/paper/1602.03001/) (2016)
- [CodeR: Issue Resolving with Multi-Agent and Task Graphs](https://mlsanity.com/paper/2406.01304/) (2024)
- [Leveraging Automated Unit Tests for Unsupervised Code Translation](https://mlsanity.com/paper/2110.06773/) (2021)
- [SpecRover: Code Intent Extraction via LLMs](https://mlsanity.com/paper/2408.02232/) (2024)
- [RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation](https://mlsanity.com/paper/2402.16667/) (2024)
- [Large Language Models for Test-Free Fault Localization](https://mlsanity.com/paper/2310.01726/) (2023)
- [RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair](https://mlsanity.com/paper/2312.15698/) (2023)
- [Automatic Code Documentation Generation Using GPT-3](https://mlsanity.com/paper/2209.02235/) (2022)
- [EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair](https://mlsanity.com/paper/2506.10484/) (2025)
- [DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal](https://mlsanity.com/paper/2503.14269/) (2025)
- [DocAgent: A Multi-Agent System for Automated Code Documentation Generation](https://mlsanity.com/paper/2504.08725/) (2025)
- [When Large Language Models Confront Repository-Level Automatic Program Repair: How Well They Done?](https://mlsanity.com/paper/2403.00448/) (2024)
- [Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Fixing](https://mlsanity.com/paper/2506.16136/) (2025)
- [Programming-by-Demonstration for Long-Horizon Robot Tasks](https://mlsanity.com/paper/2305.03129/) (2023)

## Built on by (most cited first, 6 of 6)

- [RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists](https://mlsanity.com/paper/2608.04783/) (2026)
- [SkillForge: Self-Distilling Agents for Project-Specific Issue Resolution](https://mlsanity.com/paper/2608.18933/) (2026)
- [RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue](https://mlsanity.com/paper/2607.01213/) (2026)
- [Signal Reshaping for GRPO in Weak-Feedback Agentic Code Repair](https://mlsanity.com/paper/2605.07276/) (2026)
- [Better Understanding, Better Fixes? A Study of Hallucination in LLM-based Automated Program Repair](https://mlsanity.com/paper/2609.04909/) (2026)
- [AdaRepair-Mem: Adaptive Experience Orchestration for Repository-Level Program Repair](https://mlsanity.com/paper/2609.20130/) (2026)

## Abstract (arXiv)

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.