arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2405.03256cs.SE
收藏

MARE:面向需求工程的多智能体协作框架

MARE: Multi-Agents Collaboration Framework for Requirements Engineering

Dongming Jin, Zhi Jin, Xiaohong Chen, Chunhui Wang

AI总结:

本文提出MARE框架,通过多个大语言模型智能体在需求获取、建模、验证和规格说明四个任务中协作,实验表明其生成的需求模型正确性比最先进方法提升15.4%。

摘要:

需求工程(RE)是软件开发过程中的一个关键阶段,它根据利益相关者的需求生成需求规格说明。近年来,深度学习技术在若干RE任务中取得了成功。然而,获取高质量的需求规格说明需要跨多个任务和角色的协作。在本文中,我们提出了一个名为MARE的创新框架,该框架在整个RE过程中利用大语言模型(LLMs)之间的协作。MARE将RE过程划分为四个任务:需求获取、建模、验证和规格说明。每个任务通过引入一个或两个特定智能体来执行,并且每个智能体可以执行若干动作。MARE包含五个智能体和九个动作。为了促进智能体之间的协作,MARE设计了一个工作空间,供智能体上传其生成的中间需求工件并获取所需信息。我们在五个公开案例、一个数据集以及本工作创建的四个新案例上进行了实验。我们使用三种广泛采用的指标,将MARE与三个基线方法在生成的需求模型上进行了比较。实验结果表明,MARE能够生成更正确的需求模型,并以15.4%的优势超越最先进的方法。对于生成的需求规格说明,我们从三个方面进行了人工评估,并提供了关于质量的见解。

英文摘要:

Requirements Engineering (RE) is a critical phase in the software development process that generates requirements specifications from stakeholders' needs. Recently, deep learning techniques have been successful in several RE tasks. However, obtaining high-quality requirements specifications requires collaboration across multiple tasks and roles. In this paper, we propose an innovative framework called MARE, which leverages collaboration among large language models (LLMs) throughout the entire RE process. MARE divides the RE process into four tasks: elicitation, modeling, verification, and specification. Each task is conducted by engaging one or two specific agents and each agent can conduct several actions. MARE has five agents and nine actions. To facilitate collaboration between agents, MARE has designed a workspace for agents to upload their generated intermediate requirements artifacts and obtain the information they need. We conduct experiments on five public cases, one dataset, and four new cases created by this work. We compared MARE with three baselines using three widely used metrics for the generated requirements models. Experimental results show that MARE can generate more correct requirements models and outperform the state-of-the-art approaches by 15.4%. For the generated requirements specifications, we conduct a human evaluation in three aspects and provide insights about the quality

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑