EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Towards Explorative IRBL: Combining Semantic Retrieval with LLM-Driven Iterative Code Exploration

Moumita Asad, Rafed Muhammad Yasir, Sam Malek

Proceedings of the ACM on Software Engineering · 01.10.2026 · 3 (ISSTA) · 1376-1400

DOI: 10.1145/3832151 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Software Engineering, online erschienen am 01.10.2026. Verfasst von Moumita Asad und 2 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 106 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Förderung

  • National Science Foundation

Zitieren

APA

Asad, M., Yasir, R. M., & Malek, S. (2026). Towards Explorative IRBL: Combining Semantic Retrieval with LLM-Driven Iterative Code Exploration. Proceedings of the ACM on Software Engineering, 3(ISSTA), 1376-1400. https://doi.org/10.1145/3832151

Vancouver

Asad M, Yasir RM, Malek S. Towards Explorative IRBL: Combining Semantic Retrieval with LLM-Driven Iterative Code Exploration. Proceedings of the ACM on Software Engineering. 2026;3(ISSTA):1376-1400. doi:10.1145/3832151

BibTeX
@article{Asad2026,
  author = {Asad, Moumita and Yasir, Rafed Muhammad and Malek, Sam},
  title = {Towards Explorative IRBL: Combining Semantic Retrieval with LLM-Driven Iterative Code Exploration},
  journal = {Proceedings of the ACM on Software Engineering},
  year = {2026},
  volume = {3},
  number = {ISSTA},
  pages = {1376--1400},
  doi = {10.1145/3832151}
}
Kostenlos starten →