Towards Explorative IRBL: Combining Semantic Retrieval with LLM-driven Iterative Code Exploration
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908985065472000 |
|---|---|
| author | Asad, Moumita Yasir, Rafed Muhammad Malek, Sam |
| author_facet | Asad, Moumita Yasir, Rafed Muhammad Malek, Sam |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00253 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Explorative IRBL: Combining Semantic Retrieval with LLM-driven Iterative Code Exploration Asad, Moumita Yasir, Rafed Muhammad Malek, Sam Software Engineering 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. |
| title | Towards Explorative IRBL: Combining Semantic Retrieval with LLM-driven Iterative Code Exploration |
| topic | Software Engineering |
| url | https://arxiv.org/abs/2508.00253 |