Tacke, MariusMariusTackeBusch, MatthiasMatthiasBuschAbdolazizi, Kian PhilippKian PhilippAbdolaziziEichinger, JonasJonasEichingerLinka, KevinKevinLinkaCyron, Christian J.Christian J.CyronAydin, RolandRolandAydin2026-06-152026-06-152026-06-12Machine Learning for Computational Science and Engineering 2: 27 (2026)https://hdl.handle.net/11420/63481Large language model (LLM)-based frameworks extend beyond agents; they also enable the on-demand creation of specialized scientific and engineering tools. We demonstrate this concept in the field of solid mechanics. There, so-called constitutive models describe the relationship between body deformation and mechanical stress. They are essential for both the scientific understanding and industrial application of materials. However, even recent data-driven methods of constitutive modeling, such as constitutive artificial neural networks (CANNs), still require substantial expert knowledge and human labor. We present a framework in which an LLM generates a CANN on demand, tailored to a given material class and dataset provided by the user. The framework covers LLM-based architecture selection, integration of physical constraints, and complete implementation. Evaluation on three benchmark problems demonstrates that LLM-generated CANNs achieve accuracy and generalization comparable to or greater than manually engineered counterparts, while substantially reducing the expertise required for constitutive modeling.en3005-14362026Springerhttps://creativecommons.org/licenses/by/4.0/Large language models (LLMs)Physics-constrained neural networksConstitutive artificial neural networks (CANNs)Automated model generationData-driven solid mechanicsComputer Science, Information and General Works::006: Special computer methods::006.3: Artificial Intelligence::006.31: Machine LearningJournal Article2026-06-1310.1007/s44379-026-00073-z10.15480/882.17312