cs.CENov 17, 2026

Reliability by Architecture: Agentic Workflows for Validated Multi-Physics Simulation from Natural Language

Authors: Søren Taverniers, Eric Darve, Hamdi A. Tchelepi

Organizations: Department of Mechanical Engineering, Stanford University, Stanford, CA 94305, USA · Institute for Computational and Mathematical Engineering, Stanford University, Stanford, CA 94305, USA · Department of Energy Science & Engineering, Stanford University, Stanford, CA 94305, USA

Abstract

Preparing, executing, and validating strongly coupled multi-physics simulations require expert time. Agentic workflows use large language models (LLMs) to coordinate them from natural-language descriptions, but reliability requires checks of physical consistency and fidelity to the problem description. Our agentic harness implements explicit task allocation: LLMs interpret user requests and simulator diagnostics, generate input components not covered by predefined construction rules, and propose repairs, while deterministic routines construct supported components and check inputs, edits, and results. We evaluate CO2-storage problems using the multi-physics simulator GEOS, from compositional flow to flow-poromechanics with frictional fault contact. In 80 attempts on two flow problems, grounding raises the proportion of structurally valid inputs from 5/20 to 20/20, but acceptance reaches 20/20 only with complete rule-based input preparation. With identical inputs, local repairs correct three seeded defects while preserving valid inputs. Supporting tests identify simulations passing physics checks despite differing from the problem description or reference results.

Figures & tables

Appendix figures & tables8 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Agentic Scientific Simulation: Execution-Grounded Model Construction and Reconstruction

    Feb 27, 2026Knut-Andreas Lie, Olav Møyner, Elling Svee +1Physics-Based SimulationScientific Code Generation

  2. Lean4Agent: Formal Modeling and Verification for Agent Workflow and Trajectory

    Jun 2, 2026Ruida Wang, Jerry Huang, Pengcheng Wang +3Software Engineering AgentsFormal Verification