CFD-copilot: leveraging domain-adapted large language model and model context protocol to enhance simulation automation

TL;DR

CFD-copilot introduces a specialized large language model framework with a multi-agent system and model context protocol to automate and improve the reliability of end-to-end CFD workflows for non-experts.

Contribution

This work presents a novel domain-adapted LLM framework with a multi-agent system and MCP for comprehensive CFD automation, addressing domain-specific challenges.

Findings

Enhanced automation of CFD setup and post-processing.

Improved reliability and efficiency in simulation workflows.

Validated on benchmark airfoil cases.

Abstract

Configuring computational fluid dynamics (CFD) simulations requires significant expertise in physics modeling and numerical methods, posing a barrier to non-specialists. Although automating scientific tasks with large language models (LLMs) has attracted attention, applying them to the complete, end-to-end CFD workflow remains a challenge due to its stringent domain-specific requirements. We introduce CFD-copilot, a domain-specialized LLM framework designed to facilitate natural language-driven CFD simulation from setup to post-processing. The framework employs a fine-tuned LLM to directly translate user descriptions into executable CFD setups. A multi-agent system integrates the LLM with simulation execution, automatic error correction, and result analysis. For post-processing, the framework utilizes the model context protocol (MCP), an open standard that decouples LLM reasoning from external tool execution. This modular design allows the LLM to interact with numerous specialized post-processing functions through a unified and scalable interface, improving the automation of data extraction and analysis. The framework was evaluated on benchmarks including the NACA~0012 airfoil and the three-element 30P-30N airfoil. The results indicate that domain-specific adaptation and the incorporation of the MCP jointly enhance the reliability and efficiency of LLM-driven engineering workflows.