针对企业级Java代码库，构建了能自动定位与修复问题的智能代理系统。
Resolving Java Code Repository Issues with iSWE Agent
- 采用双子代理架构，分别负责问题定位与代码修改。
- 在Multi-SWE-bench和SWE-PolyBench的Java数据集上达到当前最优准确率。
- 结合规则引擎与大模型，适合需要高可靠性维护的大型Java项目团队。
代码仓库问题的自动解决是软件工程中的关键环节。近年来，许多基于大语言模型和智能体的系统在自动化问题修复方面表现出色，但主要集中在Python语言，对其他语言如Java的支持仍不足。事实上，大量企业级软件使用Java编写，而其自动化修复研究尚不充分。本文提出iSWE Agent，一个专为Java设计的自动化问题修复系统，包含定位与编辑两个子代理，并引入基于规则的Java静态分析与转换工具。该方法在Multi-SWE-bench和SWE-PolyBench的Java测试集上均达到当前最佳性能。我们相信，通过融合规则驱动与模型驱动技术，本工作有助于提升企业级软件开发效率。
原文摘要 · Abstract (English)
Resolving issues on code repositories is an important part of software engineering. Various recent systems automatically resolve issues using large language models and agents, often with impressive performance. Unfortunately, most of these models and agents focus primarily on Python, and their performance on other programming languages is lower. In particular, a lot of enterprise software is written in Java, yet automated issue resolution for Java is under-explored. This paper introduces iSWE Agent, an automated issue resolver with an emphasis on Java. It consists of two sub-agents, one for localization and the other for editing. Both have access to novel tools based on rule-based Java static analysis and transformation. Using this approach, iSWE achieves state-of-the-art issue resolution rates across the Java splits of both Multi-SWE-bench and SWE-PolyBench. More generally, we hope that by combining the best of rule-based and model-based techniques, this paper contributes towards improving enterprise software development.
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。