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

2025-08-22

AI Summary

Cross-organizational Model-Based Systems Engineering (MBSE) collaboration faces challenges in semantic alignment of system models and weak traceability. This paper proposes a large language model (LLM)-assisted semantic integration method based on prompt engineering, innovatively integrating SysML v2’s formal semantics—including alias/import mechanisms and metadata extensions—with GPT-series LLMs to establish an iterative semantic matching process. The method enables collaborative optimization of model understanding, alignment, and validation. It realizes traceable, lightweight model integration and demonstrates significant improvements in cross-team model integration efficiency and semantic consistency within a measurement system case study. Key contributions include: (1) the first deep coupling of SysML v2’s semantic mechanisms with LLM prompt engineering; and (2) establishing a human-in-the-loop, lightweight semantic alignment paradigm that balances formal rigor with engineering practicality.

Technology Category

Machine Learning: Large Multimodal Models (LMMs)Cognitive Modeling & Cognitive Systems: Symbolic RepresentationsMultiagent Systems: Coordination and Collaboration

Application Category

Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationGraph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• Achieving semantic alignment in cross-organizational MBSE collaboration
• Integrating independently developed system models using SysML v2
• Leveraging LLMs for model understanding and integration assistance

Innovation

• LLM-assisted semantic alignment for SysML v2
• Prompt-driven approach with iterative development
• Leverages SysML v2 constructs for traceable integration