EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BLAgent : Agentic RAG for File-Level Bug Localization

Md Afif Al Mamun, Gias Uddin

ACM Transactions on Software Engineering and Methodology · 30.11.2026 · 35 (11) · 1-46

DOI: 10.1145/3830238 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 04.11.2026. Verfasst von Md Afif Al Mamun und 1 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Bug localization remains a key bottleneck for large language model (LLM)-based software maintenance, where accurately identifying faulty code is essential for debugging, root cause analysis, triage, and automated program repair (APR). File-level bug localization is especially critical in hierarchical localization and repair pipelines, where incorrect file selection can propagate to downstream stages such as function-level localization and patch generation. While Retrieval-Augmented Generation (RAG) offers a promising way to ground LLMs in repository context, existing RAG pipelines often rely on static retrieval and lack the reasoning needed to accurately identify faulty code. In this work, we present BLAgent , a novel agentic RAG framework for file-level bug localization that integrates three key ideas: (i) code structure-aware repository encoding with path-augmented Absract Syntax Tree (AST)-based chunking, (ii) dual-perspective query transformation that captures both structural and behavioral signals from bug reports, and (iii) two-phase agentic reranking that combines symbolic inspection with evidence-grounded reasoning. Unlike prior graph-based or multi-hop agentic approaches, BLAgent adopts a bounded reasoning strategy that limits LLM-based inspection and reranking to a compact, retrieval-filtered set of candidate files, avoiding open-ended repository traversal. This design balances localization accuracy with computational cost. On SWE-bench-Lite, BLAgent attains over 78% Top-1 accuracy with open source models and over 86% with a closed source model, while being over 18 \(\times\) cheaper than the strongest baseline using the same model. When integrated into an APR framework, BLAgent improves end-to-end repair success by up to 25%.

Zitieren

APA

Mamun, M. A. A., & Uddin, G. (2026). BLAgent : Agentic RAG for File-Level Bug Localization. ACM Transactions on Software Engineering and Methodology, 35(11), 1-46. https://doi.org/10.1145/3830238

Vancouver

Mamun MAA, Uddin G. BLAgent : Agentic RAG for File-Level Bug Localization. ACM Transactions on Software Engineering and Methodology. 2026;35(11):1-46. doi:10.1145/3830238

BibTeX
@article{Mamun2026,
  author = {Mamun, Md Afif Al and Uddin, Gias},
  title = {BLAgent : Agentic RAG for File-Level Bug Localization},
  journal = {ACM Transactions on Software Engineering and Methodology},
  year = {2026},
  volume = {35},
  number = {11},
  pages = {1--46},
  doi = {10.1145/3830238}
}
Kostenlos starten →