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

Genevieve Caumartin, Glaucia Melo
12/7/2025
cs.SEcs.AIcs.IR

No confident code implementation found for this paper. 5 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Meta-RAG on Large Codebases Using Code Summarization

89% match2025

Improved IR-based Bug Localization with Intelligent Relevance Feedback

85% match1 repo12025

OrcaLoca: An LLM Agent Framework for Software Issue Localization

84% match1 repo462026

Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architectures

83% match2025

Issue Localization via LLM-Driven Iterative Code Graph Searching

78% match1 repo262025

SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolution

78% match2026

Cite this paper

@article{caumartin2025reformulate,
  title  = {Reformulate, Retrieve, Localize: Agents for Repository-Level Bug Localization},
  author = {Genevieve Caumartin and Glaucia Melo},
  year   = {2025},
  eprint = {2512.07022},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2512.07022v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2512.07022.svg)](https://codeofpaper.com/paper/2512.07022)

Discussion