aceLLM-driven design of physics-constrained constitutive models: Two agents are better than one
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 fo…
Adding an Inspector agent that checks each proposal against nine physical constraints increased the share of generated constitutive models passing all checks, from 90% to 95% for Opus and from 47% to 60% for Kimi.
Even with the Inspector, only 60% of Kimi's exported models and 95% of Opus's passed all physical checks, so some generated models still violated constraints, and testing covered only three materials.
Evidence
- Peer-reviewedMachine Learning for Computational Science and Engineering2026-10-01
How should this claim be treated?
Truvace Impact Record TRV-2026-1408, v1: “LLM-driven design of physics-constrained constitutive models: Two agents are better than one.” Truvace, 2026-10-15. /record/TRV-2026-1408 (accessed at citation time). sha256 6466d20da32edaf5…
Calibration history
Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.
Certified into the record
How to verify without trusting this page
Fetch the canonical text of any version from /api/record/TRV-2026-1408 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.