用多个AI专家协作自动生成软件架构图，省时又准确。
Collaborative LLM Agents for C4 Software Architecture Design Automation
- 模拟不同角色专家对话，分步生成上下文、容器和组件视图。
- 在5个典型系统上实现快速建模，成功率高且语义一致。
- 适合想提升架构设计效率的开发团队或架构师参考。
软件架构设计是构建每个软件系统的核心环节。尽管重要，但生成主流的C4架构模型仍需手动完成，耗时费力。本文提出基于大模型的多智能体系统，通过模拟角色化专家之间的对话，分析需求并自动生成C4模型的上下文（Context）、容器（Container）和组件（Component）视图。采用混合评估框架：结合确定性检查（结构与语法完整性、C4规则一致性）与大模型作为评判者（LLM-as-a-Judge）的语义与质量评分。在五个经典系统简述上测试，该流程实现了快速建模、高编译成功率，并保持良好语义保真度。对比四种先进大模型发现其在架构设计中各有优势。本研究推动了自动化软件架构设计及其评估方法的发展。
原文摘要 · Abstract (English)
Software architecture design is a fundamental part of creating every software system. Despite its importance, producing a C4 software architecture model, the preferred notation for such architecture, remains manual and time-consuming. We introduce an LLM-based multi-agent system that automates this task by simulating a dialogue between role-specific experts who analyze requirements and generate the Context, Container, and Component views of the C4 model. Quality is assessed with a hybrid evaluation framework: deterministic checks for structural and syntactic integrity and C4 rule consistency, plus semantic and qualitative scoring via an LLM-as-a-Judge approach. Tested on five canonical system briefs, the workflow demonstrates fast C4 model creation, sustains high compilation success, and delivers semantic fidelity. A comparison of four state-of-the-art LLMs shows different strengths relevant to architectural design. This study contributes to automated software architecture design and its evaluation methods.
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。