mlsanityData to 7 Oct 2026

LocAgent: Graph-Guided LLM Agents for Code Localization

arXiv 2503.09089 ↗First posted 12 Mar 2025cs.SE cs.AI cs.CLcited by 82

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Code localization--identifying precisely where in a codebase changes need to be made--is a fundamental yet challenging task in software maintenance. Existing approaches struggle to efficiently navigate complex codebases when identifying relevant code sections. The challenge lies in bridging natural language problem descriptions with the appropriate code elements, often requiring reasoning across hierarchical structures and multiple dependencies. We introduce LocAgent, a framework that addresses code localization through graph-based representation. By parsing codebases into directed heterogeneous graphs, LocAgent creates a lightweight representation that captures code structures (files, classes, functions) and their dependencies (imports, invocations, inheritance), enabling LLM agents to effectively search and locate relevant entities through powerful multi-hop reasoning. Experimental results on real-world benchmarks demonstrate that our approach significantly enhances accuracy in code localization. Notably, our method with the fine-tuned Qwen-2.5-Coder-Instruct-32B model achieves comparable results to SOTA proprietary models at greatly reduced cost (approximately 86% reduction), reaching up to 92.7% accuracy on file-level localization while improving downstream GitHub issue resolution success rates by 12% for multiple attempts (Pass@10). Our code is available at https://github.com/gersteinlab/LocAgent.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 24 of its 48 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

24 of 48 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025OrcaLoca: An LLM Agent Framework for Software Issue Localization1 Feb
  2. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agents23 Jul
  3. 2024SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents18 Jun
  4. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May

Other references · 20

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  5. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  6. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  7. 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environmentscited by 1,134
  8. 2021Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networkscited by 176
  9. 2017A Deep Relevance Matching Model for Ad-hoc Retrievalcited by 126
  10. 2020Open-Retrieval Conversational Question Answeringcited by 99
  11. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 91
  12. 2024CodeRAG-Bench: Can Retrieval Augment Code Generation?cited by 89
8 more
  1. 2024RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graphcited by 88
  2. 2019A Deep Look into Neural Ranking Models for Information Retrievalcited by 79
  3. 2024CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databasescited by 62
  4. 2023A Quantitative and Qualitative Evaluation of LLM-Based Explainable Fault Localizationcited by 50
  5. 2024AgentFL: Scaling LLM-based Fault Localization to Project-Level Contextcited by 47
  6. 2023Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Modelscited by 35
  7. 2023Large Language Models in Fault Localisationcited by 28
  8. 2019BugSwarm: Mining and Continuously Growing a Dataset of Reproducible Failures and Fixescited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 32; 2026: 50.

82 papers.

Sort:

By area:

  1. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  2. 2025SWE-Exp: Experience-Driven Software Issue Resolutioncited by 64
  3. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 54
  4. 2025SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolutioncited by 52
  5. 2025SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agentcited by 44
  6. 2025Training Proactive and Personalized LLM Agentscited by 42
  7. 2025GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agentscited by 24
  8. 2025Issue Localization via LLM-Driven Iterative Code Graph Searchingcited by 22
  9. 2025Large Language Models are Good Relational Learnerscited by 22
  10. 2025SweRank: Software Issue Localization with Code Rankingcited by 20
  11. 2025Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approachescited by 20
  12. 2026MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discoverycited by 20
38 more
  1. 2026SWE-Explore: Benchmarking How Coding Agents Explore Repositoriescited by 20
  2. 2025Code Researcher: Deep Research Agent for Large Systems Code and Commit Historycited by 19
  3. 2025Improving Code Localization with Repository Memorycited by 19
  4. 2025GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generationcited by 17
  5. 2025Graph-Augmented Large Language Model Agents: Current Progress and Future Prospectscited by 14
  6. 2025Tool-integrated Reinforcement Learning for Repo Deep Searchcited by 14
  7. 2025Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinementcited by 9
  8. 2026Scaling Coding Agents via Atomic Skillscited by 8
  9. 2025RFCAudit: An LLM Agent for Functional Bug Detection in Network Protocolscited by 7
  10. 2025RANGER -- Repository-Level Agent for Graph-Enhanced Retrievalcited by 7
  11. 2026TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agentscited by 7
  12. 2026CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Codingcited by 7
  13. 2025Agentic Services Computingcited by 6
  14. 2025Agentic Software Issue Resolution with Large Language Models: A Surveycited by 6
  15. 2026Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCPcited by 6
  16. 2026RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Modelscited by 5
  17. 2025A Benchmark for Localizing Code and Non-Code Issues in Software Projectscited by 4
  18. 2025SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localizationcited by 4
  19. 2025GraphLocator: Graph-guided Causal Reasoning for Issue Localizationcited by 4
  20. 2026SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositoriescited by 4
  21. 2026SWE-Adept: An LLM-Based Agentic Framework for Deep Codebase Analysis and Structured Issue Resolutioncited by 4
  22. 2026FastContext: Training Efficient Repository Explorer for Coding Agentscited by 4
  23. 2026Agentic Harness for Real-World Compilerscited by 3
  24. 2026On the Role of Fault Localization Context for LLM-Based Program Repaircited by 3
  25. 2026LLM Agents Can See Code Repositoriescited by 3
  26. 2026Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repaircited by 3
  27. 2025LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recoverycited by 2
  28. 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
  29. 2025PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysiscited by 2
  30. 2026ARISE: A Repository-level Graph Representation and Toolset for Agentic Program Repair and Fault Localizationcited by 2
  31. 2026LARGER: Lexically Anchored Repository Graph Exploration and Retrievalcited by 2
  32. 2026Code Isn't Memory: A Structural Codebase Index Inside a Coding Agentcited by 2
  33. 2026SHERLOC: Structured Diagnostic Localization for Code Repair Agentscited by 2
  34. 2026What Context Does a Coding Agent Actually Need to Act?cited by 2
  35. 2026MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localizationcited by 2
  36. 2026PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agentscited by 2
  37. 2026Agent Retrieval Bench: Evaluating Repository Context Retrieval for Coding Agentscited by 2
  38. 2026Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository Firstcited by 2

50 most cited of 82 All 82 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis
  2. 2026Multi-CoLoR: Context-Aware Localization and Reasoning across Multi-Language Codebases
  3. 2024A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion
  4. 2025Meta-RAG on Large Codebases Using Code Summarization
  5. 2025Prometheus: Towards Long-Horizon Codebase Navigation for Repository-Level Problem Solving
  6. 2025Breakpoint: Scalable evaluation of system-level reasoning in LLM code agents
  7. 2025Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
  8. 2025Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models