Collaborative LLM Agents for C4 Software Architecture Design Automation

TL;DR

This paper presents an LLM-based multi-agent system that automates the creation of C4 software architecture models, significantly reducing manual effort while maintaining high quality and semantic fidelity.

Contribution

It introduces a novel multi-agent LLM framework for automated C4 architecture design and a hybrid evaluation method combining structural checks and LLM-based semantic assessment.

Findings

Fast C4 model generation demonstrated on five system briefs

High success rate in model compilation and structural integrity

Different LLMs show varied strengths in architectural tasks

Abstract

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.