Measure Twice, Locate Once: Mitigating Hallucinations in LLM-based Agents for Repository-Scale Fault Localization
FaultLens is a novel FL technique that equips an LLM-based agent with a fine-grained feedback mechanism for repository-scale fault localization, and achieves a 43.35% improvement over SoapFL and a 24.24% improvement over AutoFL in the Top-1 metric, surpassing state-of-the-art LLM-based agent methods.