Collaborative LLM Agents for C4 Software Architecture Design Automation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Szczepanik, Kamil, Chudziak, Jarosław A.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914116182999040
author Szczepanik, Kamil
Chudziak, Jarosław A.
author_facet Szczepanik, Kamil
Chudziak, Jarosław A.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_22787
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Collaborative LLM Agents for C4 Software Architecture Design Automation
Szczepanik, Kamil
Chudziak, Jarosław A.
Software Engineering
Artificial Intelligence
68T07
I.2.11; I.2.7; I.2.8
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.
title Collaborative LLM Agents for C4 Software Architecture Design Automation
topic Software Engineering
Artificial Intelligence
68T07
I.2.11; I.2.7; I.2.8
url https://arxiv.org/abs/2510.22787