首份LLM代理在软件工程中的综述，梳理技术框架与挑战
Agents in Software Engineering: Survey, Landscape, and Vision
- 提出感知-记忆-行动三模块框架，系统化归纳代理技术
- 总结现有研究在代码生成、缺陷检测等任务中的应用现状
- 适合关注AI辅助开发的工程师与研究者阅读
近年来，大语言模型（LLMs）在多个下游任务中取得显著成果，尤其在软件工程（SE）领域广泛应用。我们发现，众多结合LLM与SE的研究均以代理（agent）概念为核心，或显性或隐性地使用。然而，当前缺乏对相关工作的深入综述，难以厘清其发展脉络、分析如何利用基于LLM的代理优化各类任务，也未明确该领域的整体框架。本文首次系统综述了基于LLM的代理在软件工程中的研究，提出一个包含感知、记忆和行动三个核心模块的框架，并总结了当前融合过程中存在的挑战，进一步提出了应对挑战的未来机遇。相关论文列表已整理至GitHub仓库：https://github.com/DeepSoftwareAnalytics/Awesome-Agent4SE。
原文摘要 · Abstract (English)
In recent years, Large Language Models (LLMs) have achieved remarkable success and have been widely used in various downstream tasks, especially in the tasks of the software engineering (SE) field. We find that many studies combining LLMs with SE have employed the concept of agents either explicitly or implicitly. However, there is a lack of an in-depth survey to sort out the development context of existing works, analyze how existing works combine the LLM-based agent technologies to optimize various tasks, and clarify the framework of LLM-based agents in SE. In this paper, we conduct the first survey of the studies on combining LLM-based agents with SE and present a framework of LLM-based agents in SE which includes three key modules: perception, memory, and action. We also summarize the current challenges in combining the two fields and propose future opportunities in response to existing challenges. We maintain a GitHub repository of the related papers at: https://github.com/DeepSoftwareAnalytics/Awesome-Agent4SE.
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。