# LocAgent: Graph-Guided LLM Agents for Code Localization

arXiv: https://arxiv.org/abs/2503.09089 · HTML: https://mlsanity.com/paper/2503.09089/

## Key facts

- Cited by 86 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 24 of its 48 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [REALM: Retrieval-Augmented Language Model Pre-Training](https://mlsanity.com/paper/2002.08909/) (2020)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Text Embeddings by Weakly-Supervised Contrastive Pre-training](https://mlsanity.com/paper/2212.03533/) (2022)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks](https://mlsanity.com/paper/2112.14936/) (2021)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [A Deep Relevance Matching Model for Ad-hoc Retrieval](https://mlsanity.com/paper/1711.08611/) (2017)
- [Open-Retrieval Conversational Question Answering](https://mlsanity.com/paper/2005.11364/) (2020)
- [T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Step](https://mlsanity.com/paper/2312.14033/) (2023)
- [CodeRAG-Bench: Can Retrieval Augment Code Generation?](https://mlsanity.com/paper/2406.14497/) (2024)
- [RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph](https://mlsanity.com/paper/2410.14684/) (2024)
- [A Deep Look into Neural Ranking Models for Information Retrieval](https://mlsanity.com/paper/1903.06902/) (2019)
- [CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph Databases](https://mlsanity.com/paper/2408.03910/) (2024)
- [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)
- [OrcaLoca: An LLM Agent Framework for Software Issue Localization](https://mlsanity.com/paper/2502.00350/) (2025)
- [Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models](https://mlsanity.com/paper/2307.11224/) (2023)
- [Large Language Models in Fault Localisation](https://mlsanity.com/paper/2308.15276/) (2023)
- [BugSwarm: Mining and Continuously Growing a Dataset of Reproducible Failures and Fixes](https://mlsanity.com/paper/1903.06725/) (2019)

## Built on by (most cited first, 30 of 86)

- [From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review](https://mlsanity.com/paper/2504.19678/) (2025)
- [SWE-Exp: Experience-Driven Software Issue Resolution](https://mlsanity.com/paper/2507.23361/) (2025)
- [A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasures](https://mlsanity.com/paper/2506.19676/) (2025)
- [SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution](https://mlsanity.com/paper/2507.23348/) (2025)
- [SkyRL-Agent: Efficient RL Training for Multi-turn LLM Agent](https://mlsanity.com/paper/2511.16108/) (2025)
- [Training Proactive and Personalized LLM Agents](https://mlsanity.com/paper/2511.02208/) (2025)
- [MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery](https://mlsanity.com/paper/2606.06473/) (2026)
- [GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents](https://mlsanity.com/paper/2505.23671/) (2025)
- [Large Language Models are Good Relational Learners](https://mlsanity.com/paper/2506.05725/) (2025)
- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [Issue Localization via LLM-Driven Iterative Code Graph Searching](https://mlsanity.com/paper/2503.22424/) (2025)
- [SWE-Explore: Benchmarking How Coding Agents Explore Repositories](https://mlsanity.com/paper/2606.07297/) (2026)
- [SweRank: Software Issue Localization with Code Ranking](https://mlsanity.com/paper/2505.07849/) (2025)
- [Code Researcher: Deep Research Agent for Large Systems Code and Commit History](https://mlsanity.com/paper/2506.11060/) (2025)
- [Improving Code Localization with Repository Memory](https://mlsanity.com/paper/2510.01003/) (2025)
- [GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation](https://mlsanity.com/paper/2504.10046/) (2025)
- [Tool-integrated Reinforcement Learning for Repo Deep Search](https://mlsanity.com/paper/2508.03012/) (2025)
- [Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects](https://mlsanity.com/paper/2507.21407/) (2025)
- [Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement](https://mlsanity.com/paper/2511.05931/) (2025)
- [Scaling Coding Agents via Atomic Skills](https://mlsanity.com/paper/2604.05013/) (2026)
- [RFCAudit: An LLM Agent for Functional Bug Detection in Network Protocols](https://mlsanity.com/paper/2506.00714/) (2025)
- [RANGER -- Repository-Level Agent for Graph-Enhanced Retrieval](https://mlsanity.com/paper/2509.25257/) (2025)
- [TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents](https://mlsanity.com/paper/2602.02196/) (2026)
- [CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding](https://mlsanity.com/paper/2606.11864/) (2026)
- [Agentic Services Computing](https://mlsanity.com/paper/2509.24380/) (2025)
- [Agentic Software Issue Resolution with Large Language Models: A Survey](https://mlsanity.com/paper/2512.22256/) (2025)
- [Codebase-Memory: Tree-Sitter-Based Knowledge Graphs for LLM Code Exploration via MCP](https://mlsanity.com/paper/2603.27277/) (2026)
- [SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization](https://mlsanity.com/paper/2512.20482/) (2025)
- [RGFL: Reasoning Guided Fault Localization for Automated Program Repair Using Large Language Models](https://mlsanity.com/paper/2601.18044/) (2026)
- [FastContext: Training Efficient Repository Explorer for Coding Agents](https://mlsanity.com/paper/2606.14066/) (2026)

## 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.