Towards Explorative IRBL: Combining Semantic Retrieval with LLM-driven Iterative Code Exploration
This addresses bug localization for software developers, offering a novel approach that overcomes limitations like vocabulary mismatch and context issues in existing methods.
The paper tackles the problem of bug localization in software by proposing GenLoc, which combines semantic retrieval with LLM-driven iterative code exploration to identify buggy source files from bug reports. Results show it substantially outperforms traditional, deep learning-based, and recent LLM-based methods across multiple benchmarks, including large-scale Java and Python datasets.
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.