Interoperability between heterogeneous modeling tools remains a significant challenge in Model-Driven Engineering (MDE), particularly in the automotive domain where multiple modeling languages, as well as de facto standard proprietary and open-source tools coexist. This paper presents an LLM-driven approach for automated model interoperability by considering two relevant aspects: 1) mapping model instances to a target metamodel; 2) merging of metamodels. The proposed methodology is demonstrated through transformations involving Ecore and SysML v2 based metamodels and incorporates structural validation of generated model instances against user-defined target models. Automotive case studies illustrate the feasibility of the approach and show that large language models can significantly reduce manual transformation effort while generating structurally valid target models for cross-tool interoperability.
Blogger's Review: The LLM-driven method proposed in this paper offers a novel perspective on achieving interoperability among modeling tools in the automotive sector. The automation of model mapping and merging greatly enhances efficiency, making it a valuable approach for other domains. Particularly in collaborative environments with multiple tools, it effectively minimizes manual intervention and streamlines workflows.