一句话：提出知识驱动的多智能体框架 MAAD，用 LLM 智能体模拟架构设计角色以自动完成架构设计。
软件架构设计是软件开发的关键环节，但高质量架构的产出高度依赖人类专家经验与大量手工投入，成本高昂。尽管基于大语言模型（LLM）的智能体已在多项软件工程任务中取得显著成效，利用智能体自动化架构设计流程仍基本未被探索。为填补这一空白，本文提出并构想了一个基于知识的多智能体架构设计框架 MAAD：该框架以智能体模拟传统软件架构设计过程中的人类角色，从而将设计流程自动化；同时从三类关键来源为智能体注入知识，即已有系统设计、权威文献以及架构专家经验。通过构想 MAAD 框架，作者希望推动应用级系统开发向完全自动化迈进。本文属于愿景型工作，未报告实现与实证评估。
Architecture design is a critical step in software development. However, creating a high-quality architecture is often costly due to the significant need for human expertise and manual effort. Recently, agents built upon Large Language Models (LLMs) have achieved remarkable success in various software engineering tasks. Despite this progress, the use of agents to automate the architecture design process remains largely unexplored. To address this gap, we envision a Knowledge-based Multi-Agent Architecture Design (MAAD) framework. MAAD uses agents to simulate human roles in the traditional software architecture design process, thereby automating the design process. To empower these agents, MAAD incorporates knowledge extracted from three key sources: 1) existing system designs, 2) authoritative literature, and 3) architecture experts. By envisioning the MAAD framework, we aim to advance the full automation of application-level system development.
@inproceedings{paperbot9166,
title = {Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design},
author = {Yiran Zhang and Ruiyin Li and Peng Liang and Weisong Sun and Yang Liu},
booktitle = {FSE},
year = {2025},
doi = {10.1145/3696630.3728493}
}