Foam-Agent: Towards Automated Intelligent CFD Workflows

2025-05-08

AI Summary

To address the heavy reliance of CFD simulations on expert knowledge, cumbersome manual configuration, and low automation, this paper proposes a multi-agent-based end-to-end automation workflow system for OpenFOAM. Methodologically, it integrates retrieval-augmented generation (RAG) with hierarchical multi-index domain knowledge retrieval, dependency-aware configuration file generation that explicitly models topological parameter constraints, and an LLM-driven iterative, fully autonomous error diagnosis and repair mechanism. The system employs a collaborative multi-agent architecture grounded in configuration dependency graph modeling. Evaluated on 110 real-world simulation tasks, it achieves an 83.6% success rate—46.2 percentage points higher than baseline methods. Ablation studies show that the error correction module alone contributes a 36.4% performance gain, significantly enhancing the robustness and autonomy of CFD workflows.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

Computational Fluid Dynamics (CFD) is an essential simulation tool in various engineering disciplines, but it often requires substantial domain expertise and manual configuration, creating barriers to entry. We present Foam-Agent, a multi-agent framework that automates complex OpenFOAM-based CFD simulation workflows from natural language inputs. Our innovation includes (1) a hierarchical multi-index retrieval system with specialized indices for different simulation aspects, (2) a dependency-aware file generation system that provides consistency management across configuration files, and (3) an iterative error correction mechanism that diagnoses and resolves simulation failures without human intervention. Through comprehensive evaluation on the dataset of 110 simulation tasks, Foam-Agent achieves an 83.6% success rate with Claude 3.5 Sonnet, significantly outperforming existing frameworks (55.5% for MetaOpenFOAM and 37.3% for OpenFOAM-GPT). Ablation studies demonstrate the critical contribution of each system component, with the specialized error correction mechanism providing a 36.4% performance improvement. Foam-Agent substantially lowers the CFD expertise threshold while maintaining modeling accuracy, demonstrating the potential of specialized multi-agent systems to democratize access to complex scientific simulation tools. The code is public at https://github.com/csml-rpi/Foam-Agent

Problem

• Automates OpenFOAM-based CFD workflows from natural language inputs
• Reduces need for manual configuration and domain expertise in CFD
• Diagnoses and resolves simulation failures without human intervention

Innovation

• Hierarchical multi-index retrieval system for simulations
• Dependency-aware file generation ensuring consistency
• Iterative error correction without human intervention