发表机构
New York University; University of British Columbia（纽约大学; 不列颠哥伦比亚大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究利用大语言模型智能体，基于人类指定的规范自动构建电化学器件多物理场模型，在开源Julia中实现与COMSOL高度一致的结果，使物理描述而非代码成为建模核心。
AI 中文摘要
多物理场连续介质模型是研究电化学器件的强大工具，能够实现反应器的计算机模拟设计，并解析决定器件性能但难以通过实验测量的局部pH、电势和浓度场。然而，构建此类模型需要大量的数值计算专业知识或依赖专有软件。在此，我们证明前沿大语言模型智能体能够消除这一实现负担，同时将底层物理过程保持在研究人员的控制之下。以多孔气体扩散电极中一维电化学CO2还原为CO作为测试案例，我们开发了一种机器可读、由人类指定的建模框架，其中包含控制方程、参数、数值方法、逻辑构建阶段和人类可验证的检查点。基于该规范，智能体可重复地在开源Julia语言中构建完整的多物理场模型。独立构建的模型（包括完全自主的智能体构建模型）与等效的COMSOL实现相比，峰值CO分电流密度差异在0.7%以内，模型之间相互差异在0.04%以内。系统性植入的错误证明了显式规范对可重复性的重要性，并揭示了智能体在调试模型物理方面的能力与局限性。该框架建立了一种更透明的多物理场建模方法，其中物理描述和控制方程（而非专门代码）成为计算模型开发的主要输入。
英文摘要
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. However, constructing such models requires substantial numerical expertise or reliance on proprietary software. Here, we show that frontier large language model agents can remove this implementation burden while keeping the underlying physics under researcher control. 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. From this specification, the agent reproducibly constructs complete multiphysics models in open-source Julia. Independently built models, including fully autonomous agent-built models, agree with an equivalent COMSOL implementation to within 0.7% of the peak CO partial current density, and with one another to within 0.04%. Systematically planted errors demonstrate the importance of explicit specifications for reproducibility and reveal the agent's capabilities and limitations in debugging model physics. This framework establishes a more transparent approach to multiphysics modeling in which physical descriptions and governing equations, rather than specialized code, become the primary inputs for computational model development.
Comments25 pages, 6 figures, Supplementary Information and implementation guide provided as ancillary files
