Towards Explorative IRBL: Combining Semantic Retrieval with LLM-Driven Iterative Code Exploration
Open Access
- 1 October 2026
- journal article
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Software Engineering
- Vol. 3 (ISSTA) , 1376-1400
Abstract
Information Retrieval-based Bug Localization (IRBL) aims to identify buggy source files for a given bug report. Traditional and deep learning-based IRBL techniques often suffer from vocabulary mismatch and dependence on project-specific metadata. In contrast, recent Large Language Model (LLM)-based approaches struggle to provide appropriate context to the model: they either restrict analysis to a fixed set of candidate files, overwhelm the model with repository-wide information, or rely on explicit bug report cues to guide context collection. To address these issues, we propose GenLoc, a technique that combines semantic retrieval with LLM-driven code-exploration functions to iteratively analyze the code base and identify buggy files. We evaluate GenLoc on three complementary benchmarks, including large-scale and recent Java datasets as well as the Python based SWE-bench Lite dataset. Results demonstrate that GenLoc substantially outperforms traditional IRBL, deep learning-based approaches and recent LLM-based methods, while also localizing bugs that other techniques fail to detect.Keywords
All Related Versions
Funding Information
- National Science Foundation (2211790)
- National Science Foundation (2106306)
This publication has 95 references indexed in Scilit:
- SBEST: Spectrum-based fault localization without fault-triggering testsEmpirical Software Engineering, 2025
- Multi-view adaptive contrastive learning for information retrieval based fault localizationAutomated Software Engineering, 2025
- Handbook of Software Fault Localization2023
- bjXnet: an improved bug localization model based on code property graph and attention mechanismAutomated Software Engineering, 2023
- Modeling function-level interactions for file-level bug localizationEmpirical Software Engineering, 2022
- An empirical study of the effectiveness of IR-based bug localization for large-scale industrial projectsEmpirical Software Engineering, 2022
- Are datasets for information retrieval-based bug localization techniques trustworthy?Empirical Software Engineering, 2021
- AmaLgam+: Composing Rich Information Sources for Accurate Bug LocalizationJournal of Software: Evolution and Process, 2016
- Bug localization using latent Dirichlet allocationInformation and Software Technology, 2010
- Mann‐Whitney U Test2010