# Reformulate, Retrieve, Localize: Agents for Repository-Level Bug Localization

arXiv: https://arxiv.org/abs/2512.07022 · HTML: https://mlsanity.com/paper/2512.07022/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 41 references that are in the map.
- First posted on arXiv 7 Dec 2025.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 15 of 15)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation](https://mlsanity.com/paper/2305.01210/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism](https://mlsanity.com/paper/2407.10457/) (2024)
- [SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution](https://mlsanity.com/paper/2501.05040/) (2025)
- [LocAgent: Graph-Guided LLM Agents for Code Localization](https://mlsanity.com/paper/2503.09089/) (2025)
- [Long Code Arena: a Set of Benchmarks for Long-Context Code Models](https://mlsanity.com/paper/2406.11612/) (2024)
- [CodeAgent: Autonomous Communicative Agents for Code Review](https://mlsanity.com/paper/2402.02172/) (2024)
- [Improving IR-Based Bug Localization with Context-Aware Query Reformulation](https://mlsanity.com/paper/1808.00594/) (2018)
- [A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion](https://mlsanity.com/paper/2409.13642/) (2024)
- [The Forgotten Role of Search Queries in IR-based Bug Localization: An Empirical Study](https://mlsanity.com/paper/2108.05341/) (2021)
- [A Systematic Review of Automated Query Reformulations in Source Code Search](https://mlsanity.com/paper/2108.09646/) (2021)
- [Toward Rapid Bug Resolution for Android Apps](https://mlsanity.com/paper/2312.15318/) (2023)

## Abstract (arXiv)

Bug localization remains a critical yet time-consuming challenge in large-scale software repositories. Traditional information retrieval-based bug localization (IRBL) methods rely on unchanged bug descriptions, which often contain noisy information, leading to poor retrieval accuracy. Recent advances in large language models (LLMs) have improved bug localization through query reformulation, yet the effect on agent performance remains unexplored. In this study, we investigate how an LLM-powered agent can improve file-level bug localization via lightweight query reformulation and summarization. We first employ an open-source, non-fine-tuned LLM to extract key information from bug reports, such as identifiers and code snippets, and reformulate queries pre-retrieval. Our agent then orchestrates BM25 retrieval using these preprocessed queries, automating localization workflow at scale. Using the best-performing query reformulation technique, our agent achieves 35% better ranking in first-file retrieval than our BM25 baseline and up to +22% file retrieval performance over SWE-agent.