Options
LLM-driven design of physics-constrained constitutive models: Two agents are better than one
Citation Link: https://doi.org/10.15480/882.18704
Publikationstyp
Journal Article
Date Issued
2026-10-01
Sprache
English
Author(s)
TORE-DOI
Volume
2
Article Number
51
Citation
Machine Learning for Computational Science and Engineering 2: 51 (2026)
Publisher DOI
Publisher
Springer
Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics, machine learning, and scientific programming. Large language models (LLMs) have recently been shown to lower this barrier by generating constitutive models on demand, but existing single-agent pipelines lack systematic checks that the resulting models respect fundamental physical laws. To close this gap, we introduce 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. We demonstrate this concept with constitutive artificial neural networks (CANNs) and benchmark it on brain tissue and rubber as isotropic materials, and on porcine skin tissue as a transversely isotropic material with a preferred fiber direction, using two different LLM backbones (Claude Opus 4.7 and Kimi K2.5). Whether a generated model satisfies the physical constraints is assessed numerically, by probing each constraint across a broad sample of deformation states, rotations, and perturbation directions. Adding the Inspector raises the share of exported models that pass all these checks from 90% to 95% for Opus and from 47% to 60% for Kimi. In addition, the generated models are on par with or even surpass expert-designed models in accuracy, extrapolate reliably beyond the training data, and generalize remarkably well to unseen loading paths. Separating generation from inspection thus turns LLM-driven constitutive modeling into a substantially more trustworthy process. The paradigm is deliberately technique-agnostic and scales automatically with advances in LLM capability, opening a promising path toward automated, physics-aware model discovery.
DDC Class
620.11: Engineering Materials
006.3: Artificial Intelligence
Publication version
publishedVersion
Loading...
Name
44379_2026_Article_99.pdf
Type
Main Article
Size
4.33 MB
Format
Adobe PDF