Software Engineering Empirical Research Radar

Measure Twice, Locate Once: Mitigating Hallucinations in LLM-based Agents for Repository-Scale Fault Localization

Paper detail page in SEER Radar.

Authors

Feiyue Chen, Guowei Yang, Cheryl Lee, Zhanming Jie, Yuqi Chen

Venue / Year

TOSEM 2026

Topics

Debugging / Fault Localization / Diagnosis / Repair; AI / LLM for SE; Software Agents

Abstract / Summary

FaultLens is a repository-scale fault-localization agent designed to reduce both extrinsic and intrinsic hallucinations. It validates extracted locations, uses completion rules and self-checking, and strengthens location identification. On Defects4J, the study reports Top-1 gains of 43.35% over SoapFL and 24.24% over AutoFL, with additional evidence across programming languages and LLM backends.

External Links

DOI / Publisher Original Source

Read PDF

Open / Download Local PDF Original Source
转载自原公开来源,仅供学术研究阅读;请以原来源为准。