System Architects Are not Alone Anymore: Automatic System Modeling with AI
Ludovic Apvrille, Bastien Sultan
2024
Abstract
System development cycles typically follow a V-cycle, where modelers first analyze a system specification before proposing its design. When utilizing SysML, this process predominantly involves transforming natural language (the system specification) into various structural and behavioral views employing SysML diagrams. With their proficiency in interpreting natural text and generating results in predetermined formats, Large Language Models (LLMs) could assist such development cycles. This paper introduces a framework where LLMs can be leveraged to automatically construct both structural and behavioral SysML diagrams from system specifications. Through multiple examples, the paper underscores the potential utility of LLMs in this context, highlighting the necessity for feeding these models with a well-defined knowledge base and an automated feedback loop for better outcomes.
DownloadPaper Citation
in Harvard Style
Apvrille L. and Sultan B. (2024). System Architects Are not Alone Anymore: Automatic System Modeling with AI. In Proceedings of the 12th International Conference on Model-Based Software and Systems Engineering - Volume 1: MODELSWARD; ISBN 978-989-758-682-8, SciTePress, pages 27-38. DOI: 10.5220/0012320100003645
in Bibtex Style
@conference{modelsward24,
author={Ludovic Apvrille and Bastien Sultan},
title={System Architects Are not Alone Anymore: Automatic System Modeling with AI},
booktitle={Proceedings of the 12th International Conference on Model-Based Software and Systems Engineering - Volume 1: MODELSWARD},
year={2024},
pages={27-38},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012320100003645},
isbn={978-989-758-682-8},
}
in EndNote Style
TY - CONF
JO - Proceedings of the 12th International Conference on Model-Based Software and Systems Engineering - Volume 1: MODELSWARD
TI - System Architects Are not Alone Anymore: Automatic System Modeling with AI
SN - 978-989-758-682-8
AU - Apvrille L.
AU - Sultan B.
PY - 2024
SP - 27
EP - 38
DO - 10.5220/0012320100003645
PB - SciTePress