OrcaLoca提升代码问题定位准确率，让大模型更懂精准找错。
OrcaLoca: An LLM Agent Framework for Software Issue Localization
- 通过优先级调度与相关性评分分解定位动作，提升搜索效率。
- 在SWE-bench Lite上函数匹配率达65.33%，刷新开源新纪录。
- 适合需要自动修复与代码定位的开发团队使用。
大型语言模型（LLM）代理正推动自主软件工程发展，实现自动化编码、问题修复与功能优化。然而，精准定位——即通过导航到相关代码段来识别问题——仍是重大挑战。现有方法因缺乏有效整合LLM代理与精确代码搜索机制而表现不佳。本文提出OrcaLoca框架，通过引入基于优先级的调度策略、动作分解结合相关性评分、以及距离感知的上下文裁剪，显著提升问题定位准确性。实验表明，OrcaLoca在SWE-bench Lite上的函数匹配率达65.33%，成为当前开源最优水平；其补丁生成模块集成后，使某开源框架的最终解决率提升6.33个百分点。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。