B. Combemale, J. Kienzle, G. Mussbacher, P. Archambault, J.M. Bruel, L. Burgueño, B. H C Cheng, L. Cleophas, G. Engels, D. Foures, S. Klikovits, V. Kulkarni, J. Michael, S. Mosser, H. Sahraoui, E. Syriani, A. Wortmann: On the Challenges of Integrating Digital Twins, 3rd International Conference on Engineering Digital Twins (EDTconf 2025) co-located with MODELS 2025, October 6-7, 2025, Grand Valley State University, Grand Rapids, MI, USA and Virtual. document, Doi: 10.1109/MODELS-C68889.2025.00042
In the past two decades, a range of model versioning workflows have been proposed. Standard workflows are based on three-way model merging, which allows reasoning on potentially conflicting changes in concurrently developed model versions. However, the considered conflicts that can be detected are mostly targeting the syntactic level of models, such as update/update or delete/usage conflicts. In contrast, unintended semantic inconsistencies often remain unnoticed as detection mechanisms lack the semantic awareness of the modeling language or modeled domain. The resolution of such conflicts remains a manual task.
In this paper, we explore how Large Language Models (LLMs) can augment model versioning workflows by supporting conflict detection and resolution. In particular, we present an LLM-enhanced solution for detecting conflicts in the three-way model merging setting. Drawing on a collection of conflict types from prior literature, we demonstrate how an LLM assistant can 1) pinpoint conflicting changes and 2) provide resolution options with clear rationales and explanations of their implications. Our results indicate that the LLMs’ access to a broad range of domains and modeling languages can help find and resolve complex versioning conflicts. Our implementation combines the industrial tool LemonTree for analyzing models and model changes, with a GPT-4o (LLM) assistant primed with relevant context to detect and resolve conflicts. We conclude by discussing directions for future research to improve model versioning workflows using LLMs.