SwarmFoam: An OpenFOAM Multi-Agent System Based on Multiple Types of Large Language Models

TL;DR

SwarmFoam is a novel multi-agent framework that enhances CFD simulations by integrating multi-modal perception, error correction, and retrieval-augmented generation, demonstrating high adaptability and promising results in complex scenarios.

Contribution

It introduces SwarmFoam, a multi-agent system that combines advanced perception and processing capabilities to improve the accuracy and complexity of CFD simulations using large language models.

Findings

Overall pass rate of 84% across 25 test cases

High pass rate of 86.7% for multi-modal input cases

Demonstrates adaptability to diverse simulation inputs

Abstract

Numerical simulation is one of the mainstream methods in scientific research, typically performed by professional engineers. With the advancement of multi-agent technology, using collaborating agents to replicate human behavior shows immense potential for intelligent Computational Fluid Dynamics (CFD) simulations. Some muti-agent systems based on Large Language Models have been proposed. However, they exhibit significant limitations when dealing with complex geometries. This paper introduces a new multi-agent simulation framework, SwarmFoam. SwarmFoam integrates functionalities such as Multi-modal perception, Intelligent error correction, and Retrieval-Augmented Generation, aiming to achieve more complex simulations through dual parsing of images and high-level instructions. Experimental results demonstrate that SwarmFoam has good adaptability to simulation inputs from different modalities. The overall pass rate for 25 test cases was 84%, with natural language and multi-modal input cases achieving pass rates of 80% and 86.7%, respectively. The work presented by SwarmFoam will further promote the development of intelligent agent methods for CFD.