MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing

TL;DR

MetaOpenFOAM 2.0 utilizes Chain of Thought decomposition with Large Language Models to automate CFD simulation and post-processing, significantly improving accuracy and accessibility for non-expert users.

Contribution

The paper introduces MetaOpenFOAM 2.0, a novel LLM-based framework that enhances CFD automation through COT-driven reasoning and iterative verification, outperforming previous versions.

Findings

Achieved an Executability score of 6.3/7 and an 86.9% pass rate.

Proved cost-effective at $0.15 per case.

COT-driven decomposition improves task performance.

Abstract

Computational Fluid Dynamics (CFD) is widely used in aerospace, energy, and biology to model fluid flow, heat transfer, and chemical reactions. While Large Language Models (LLMs) have transformed various domains, their application in CFD remains limited, particularly for complex tasks like post-processing. To bridge this gap, we introduce MetaOpenFOAM 2.0, which leverages Chain of Thought (COT) decomposition and iterative verification to enhance accessibility for non-expert users through natural language inputs. Tested on a new benchmark covering simulation (fluid flow, heat transfer, combustion) and post-processing (extraction, visualization), MetaOpenFOAM 2.0 achieved an Executability score of 6.3/7 and a pass rate of 86.9%, significantly outperforming MetaOpenFOAM 1.0 (2.1/7, 0%). Additionally, it proved cost-efficient, averaging $0.15 per case. An ablation study confirmed that COT-driven decomposition and iterative refinement substantially improved task performance. Furthermore, scaling laws showed that increasing COT steps enhanced accuracy while raising token usage, aligning with LLM post-training scaling trends. These results highlight the transformative potential of LLMs in automating CFD workflows for industrial and research applications. Code is available at https://github.com/Terry-cyx/MetaOpenFOAM