Collaborative Model-based Systems Engineering between companies is becoming increasingly important. The utilization of the modeling possibilities of the standard language SysML v2 and the multilateral data exchange via Dataspaces open new possibilities for efficient collaboration. Based on systemic approaches, a modeling concept for decomposing the system into sub-systems is developed as a basis for the exchange. In addition, based on the analysis of collaboration processes in the context of Systems Engineering, an architectural approach with a SysML editor and Dataspace for the exchange is elaborated. The architecture is implemented on the basis of open-source solutions. The investigations are based on an application example from precision engineering. The potential and challenges are discussed.

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.