LocAgent: Graph-Guided LLM Agents for Code Localization
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910921417293824 |
|---|---|
| author | Chen, Zhaoling Tang, Xiangru Deng, Gangda Wu, Fang Wu, Jialong Jiang, Zhiwei Prasanna, Viktor Cohan, Arman Wang, Xingyao |
| author_facet | Chen, Zhaoling Tang, Xiangru Deng, Gangda Wu, Fang Wu, Jialong Jiang, Zhiwei Prasanna, Viktor Cohan, Arman Wang, Xingyao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09089 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LocAgent: Graph-Guided LLM Agents for Code Localization Chen, Zhaoling Tang, Xiangru Deng, Gangda Wu, Fang Wu, Jialong Jiang, Zhiwei Prasanna, Viktor Cohan, Arman Wang, Xingyao Software Engineering Artificial Intelligence Computation and Language 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. |
| title | LocAgent: Graph-Guided LLM Agents for Code Localization |
| topic | Software Engineering Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2503.09089 |