SysTemp: A Multi-Agent System for Template-Based Generation of SysML v2

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Bouamra, Yasmine, Yun, Bruno, Poisson, Alexandre, Armetta, Frédéric
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911025800937472
author Bouamra, Yasmine
Yun, Bruno
Poisson, Alexandre
Armetta, Frédéric
author_facet Bouamra, Yasmine
Yun, Bruno
Poisson, Alexandre
Armetta, Frédéric
contents The automatic generation of SysML v2 models represents a major challenge in the engineering of complex systems, particularly due to the scarcity of learning corpora and complex syntax. We present SysTemp, a system aimed at facilitating and improving the creation of SysML v2 models from natural language specifications. It is based on a multi-agent system, including a template generator that structures the generation process. We discuss the advantages and challenges of this system through an evaluation, highlighting its potential to improve the quality of the generations in SysML v2 modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2506_21608
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SysTemp: A Multi-Agent System for Template-Based Generation of SysML v2
Bouamra, Yasmine
Yun, Bruno
Poisson, Alexandre
Armetta, Frédéric
Computation and Language
Artificial Intelligence
The automatic generation of SysML v2 models represents a major challenge in the engineering of complex systems, particularly due to the scarcity of learning corpora and complex syntax. We present SysTemp, a system aimed at facilitating and improving the creation of SysML v2 models from natural language specifications. It is based on a multi-agent system, including a template generator that structures the generation process. We discuss the advantages and challenges of this system through an evaluation, highlighting its potential to improve the quality of the generations in SysML v2 modeling.
title SysTemp: A Multi-Agent System for Template-Based Generation of SysML v2
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.21608