#machine learning
May 2026
LLM-driven design of physics-constrained constitutive models: two agents are better than one
This work introduces the first multi-agent LLM-driven approach for constitutive model generation: a Creator agent proposes a model tailored to the data, while an Inspector agent critically audits each proposal against nine physical constraints and returns it for refinement whenever a violation is detected.
M. Tacke, Matthias Busch, Kian P. Abdolazizi et al.
· arXiv.org · 0 citations