# A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion

arXiv: https://arxiv.org/abs/2409.13642 · HTML: https://mlsanity.com/paper/2409.13642/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 81 references that are in the map.
- First posted on arXiv 20 Sep 2024.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [Gated Graph Sequence Neural Networks](https://mlsanity.com/paper/1511.05493/) (2015)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Character-LLM: A Trainable Agent for Role-Playing](https://mlsanity.com/paper/2310.10158/) (2023)
- [Hallucination is Inevitable: An Innate Limitation of Large Language Models](https://mlsanity.com/paper/2401.11817/) (2024)
- [Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf](https://mlsanity.com/paper/2309.04658/) (2023)
- [ChatUniTest: A Framework for LLM-Based Test Generation](https://mlsanity.com/paper/2305.04764/) (2023)
- [RecurrentGPT: Interactive Generation of (Arbitrarily) Long Text](https://mlsanity.com/paper/2305.13304/) (2023)
- [Large Language Models for Test-Free Fault Localization](https://mlsanity.com/paper/2310.01726/) (2023)
- [A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localization](https://mlsanity.com/paper/2308.05487/) (2023)
- [AgentFL: Scaling LLM-based Fault Localization to Project-Level Context](https://mlsanity.com/paper/2403.16362/) (2024)
- [UniDebugger: Hierarchical Multi-Agent Framework for Unified Software Debugging](https://mlsanity.com/paper/2404.17153/) (2024)
- [SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents](https://mlsanity.com/paper/2403.15852/) (2024)
- [Large Language Models in Fault Localisation](https://mlsanity.com/paper/2308.15276/) (2023)
- [Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation](https://mlsanity.com/paper/2409.03271/) (2024)
- [Fault Localization with Code Coverage Representation Learning](https://mlsanity.com/paper/2103.00270/) (2021)
- [An Empirical Study of Fault Localization Families and Their Combinations](https://mlsanity.com/paper/1803.09939/) (2018)
- [An Exploratory Study of Debugging Episodes](https://mlsanity.com/paper/2105.02162/) (2021)

## Built on by (most cited first, 9 of 9)

- [Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents](https://mlsanity.com/paper/2412.18371/) (2024)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [From Trace to Line: LLM Agent for Real-World OSS Vulnerability Localization](https://mlsanity.com/paper/2510.02389/) (2025)
- [HAFixAgent: History-Aware Program Repair Agent](https://mlsanity.com/paper/2511.01047/) (2025)
- [CAMB: A comprehensive industrial LLM benchmark on civil aviation maintenance](https://mlsanity.com/paper/2508.20420/) (2025)
- [AutoLogger: A Multi-Agent Framework for the End-to-End Automated Logging](https://mlsanity.com/paper/2511.18528/) (2025)
- [Reformulate, Retrieve, Localize: Agents for Repository-Level Bug Localization](https://mlsanity.com/paper/2512.07022/) (2025)
- [Hierarchical Fault Detection and Diagnosis for Transformer Architectures](https://mlsanity.com/paper/2604.28118/) (2026)
- [Catching Developers in the Flow: Low-Latency Agentic Program Repair at Google Scale](https://mlsanity.com/paper/2610.07289/) (2026)

## Abstract (arXiv)

Identifying and resolving software faults remains a challenging and resource-intensive process. Traditional fault localization techniques, such as Spectrum-Based Fault Localization (SBFL), leverage statistical analysis of test coverage but often suffer from limited accuracy. While learning-based approaches improve fault localization, they demand extensive training datasets and high computational resources. Recent advances in Large Language Models (LLMs) offer new opportunities by enhancing code understanding and reasoning. However, existing LLM-based fault localization techniques face significant challenges, including token limitations, performance degradation with long inputs, and scalability issues in complex software systems. To overcome these obstacles, we propose LLM4FL, a multi-agent fault localization framework that utilizes three specialized LLM agents. First, the Context Extraction Agent applies an order-sensitive segmentation strategy to partition large coverage data within the LLM's token limit, analyze failure context, and prioritize failure-related methods. The Debugger Agent then processes the extracted data, which employs graph-based retrieval-augmented code navigation to reason about failure causes and rank suspicious methods. Finally, the Reviewer Agent re-evaluates the identified faulty methods using verbal reinforcement learning, engaging in self-criticism and iterative refinement. Evaluated on the Defects4J (V2.0.0) benchmark, which includes 675 faults from 14 Java projects, LLM4FL achieves an 18.55% improvement in Top-1 accuracy over AutoFL and 4.82% over SoapFL. It outperforms supervised techniques such as DeepFL and Grace, all without requiring task-specific training. Furthermore, its coverage segmentation and prompt chaining strategies enhance performance, increasing Top-1 accuracy by up to 22%.