Recent developments in Large Language Model (LLM) agents are revolutionizing Autonomous Software Engineering (ASE), enabling automated coding, problem fixes, and feature improvements. However, localization -- precisely identifying software problems by navigating to relevant code sections -- remains a significant challenge. Current approaches often yield suboptimal results due to a lack of effective integration between LLM agents and precise code search mechanisms. This paper introduces OrcaLoca, an LLM agent framework that improves accuracy for software issue localization by integrating priority-based scheduling for LLM-guided action, action decomposition with relevance scoring, and distance-aware context pruning. Experimental results demonstrate that OrcaLoca becomes the new open-source state-of-the-art (SOTA) in function match rate (65.33%) on SWE-bench Lite. It also improves the final resolved rate of an open-source framework by 6.33 percentage points through its patch generation integration.
@article{arxiv.2502.00350,
title = {OrcaLoca: An LLM Agent Framework for Software Issue Localization},
author = {Zhongming Yu and Hejia Zhang and Yujie Zhao and Hanxian Huang and Matrix Yao and Ke Ding and Jishen Zhao},
journal= {arXiv preprint arXiv:2502.00350},
year = {2025}
}