一句话：提出 LingmaAgent，利用知识图谱和 MCTS 让 LLM agent 全面探索仓库，显著提升自动化 issue 解决效果。
现有基于大语言模型的软件工程 agent 主要关注局部代码信息，难以全面理解整个软件仓库以有效解决 issue。本文提出 Alibaba LingmaAgent，一种面向仓库级理解的自动化 issue 解决方法。它采用自顶向下方式将关键仓库信息浓缩为知识图谱以降低复杂度，并引入基于蒙特卡洛树搜索的策略，使 agent 能够探索和理解整个仓库。Agent 被引导利用仓库级知识进行总结、分析和规划，动态获取信息并为真实 GitHub issue 生成补丁。在 SWE-bench Lite 基准上，LingmaAgent 相比 SWE-agent 取得 18.5% 的相对提升。在阿里云生产部署中，它自动解决了 16.9% 的内部问题，人工干预后解决率达 43.3%。此外，作者开源了 Python 原型供工业界参考。
This paper presents Alibaba LingmaAgent, a novel Automated Software Engineering method designed to comprehensively understand and utilize whole software repositories for issue resolution. Deployed in TONGYI Lingma, an IDE-based coding assistant developed by Alibaba Cloud, LingmaAgent addresses the limitations of existing LLM-based agents that primarily focus on local code information. Our approach introduces a top-down method to condense critical repository information into a knowledge graph, reducing complexity, and employs a Monte Carlo tree search based strategy enabling agents to explore and understand entire repositories. We guide agents to summarize, analyze, and plan using repository-level knowledge, allowing them to dynamically acquire information and generate patches for real-world GitHub issues. In extensive experiments, LingmaAgent demonstrated significant improvements, achieving an 18.5% relative improvement on the SWE-bench Lite benchmark compared to SWE-agent. In production deployment and evaluation at Alibaba Cloud, LingmaAgent automatically resolved 16.9% of in-house issues faced by development engineers, and solved 43.3% of problems after manual intervention. Additionally, we have open-sourced a Python prototype of LingmaAgent for reference by other industrial developers 1. In fact, LingmaAgent has been used as a developed reference by many subsequently agents.
@inproceedings{paperbot9080,
title = {Alibaba LingmaAgent: Improving Automated Issue Resolution via Comprehensive Repository Exploration},
author = {Yingwei Ma and Qingping Yang and Rongyu Cao and Binhua Li and Fei Huang and Yongbin Li},
booktitle = {FSE},
year = {2025},
doi = {10.1145/3696630.3728549}
}