LLM-Assisted Generation of Transparent, Open-Source Multiphysics Models of Electrochemical Devices

Key points

• Here, we show that frontier large language model agents can remove this implementation burden while keeping the underlying physics under researcher control.1
• Using one-dimensional electrochemical CO2 reduction to CO in a porous gas diffusion electrode as a test case, we develop a machine-readable, human-specified modeling harness containing governing equations, parameters, numerical methods, logical build stages, and human-verifiable checkpoints.1
• From this specification, the agent reproducibly constructs complete multiphysics models in open-source Julia.1
• Systematically planted errors demonstrate the importance of explicit specifications for reproducibility and reveal the agent's capabilities and limitations in debugging model physics.1

Sources (1)

• [1]LLM-Assisted Generation of Transparent, Open-Source Multiphysics Models of Electrochemical Devices
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 04:11 PM

  Multiphysics continuum models are powerful tools for studying electrochemical devices, enabling in silico reactor design and resolution of local pH, potential, and concentration fields that govern device performance but are difficult to measure experimentally.

  Here, we show that frontier large language model agents can remove this implementation burden while keeping the underlying physics under researcher control.

Extractive summary: sentences quoted from the sources.