LLM-Assisted Semantic Alignment and Integration in Collaborative Model-Based Systems Engineering Using SysML v2

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Zirui, Husung, Stephan, Wang, Haoze
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866908829628760064
author Li, Zirui
Husung, Stephan
Wang, Haoze
author_facet Li, Zirui
Husung, Stephan
Wang, Haoze
contents Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across independently developed system models. SysML v2 introduces enhanced structural modularity and formal semantics, offering a stronger foundation for interoperable modeling. Meanwhile, GPT-based Large Language Models (LLMs) provide new capabilities for assisting model understanding and integration. This paper proposes a structured, prompt-driven approach for LLM-assisted semantic alignment of SysML v2 models. The core contribution lies in the iterative development of an alignment approach and interaction prompts, incorporating model extraction, semantic matching, and verification. The approach leverages SysML v2 constructs such as alias, import, and metadata extensions to support traceable, soft alignment integration. It is demonstrated with a GPT-based LLM through an example of a measurement system. Benefits and limitations are discussed.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16181
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-Assisted Semantic Alignment and Integration in Collaborative Model-Based Systems Engineering Using SysML v2
Li, Zirui
Husung, Stephan
Wang, Haoze
Software Engineering
Artificial Intelligence
Systems and Control
Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across independently developed system models. SysML v2 introduces enhanced structural modularity and formal semantics, offering a stronger foundation for interoperable modeling. Meanwhile, GPT-based Large Language Models (LLMs) provide new capabilities for assisting model understanding and integration. This paper proposes a structured, prompt-driven approach for LLM-assisted semantic alignment of SysML v2 models. The core contribution lies in the iterative development of an alignment approach and interaction prompts, incorporating model extraction, semantic matching, and verification. The approach leverages SysML v2 constructs such as alias, import, and metadata extensions to support traceable, soft alignment integration. It is demonstrated with a GPT-based LLM through an example of a measurement system. Benefits and limitations are discussed.
title LLM-Assisted Semantic Alignment and Integration in Collaborative Model-Based Systems Engineering Using SysML v2
topic Software Engineering
Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2508.16181