ChatCFD: an End-to-End CFD Agent with Domain-specific Structured Thinking

2025-05-28

AI Summary

CFD simulation remains inaccessible to non-experts due to its operational complexity and heavy reliance on domain expertise. To address this, we propose the first end-to-end large language model (LLM)-based agent specifically designed for CFD, enabling users to automatically configure and execute OpenFOAM simulations via natural language queries or literature inputs. Our method introduces a structured CFD reasoning framework that integrates a domain-specific knowledge graph, structured prompt engineering, LLM inference, and OpenFOAM workflow orchestration—augmented by a configuration validation and error self-reflection module to ensure robustness. Experiments demonstrate that the agent fully reproduces published CFD results across multiple benchmark cases. Notably, it achieves significantly higher success rates than general-purpose LLMs on unseen, complex flow scenarios, substantially lowering the barrier to practical CFD adoption.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• 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: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search

Abstract

Computational Fluid Dynamics (CFD) is essential for scientific and engineering advancements but is limited by operational complexity and the need for extensive expertise. This paper presents ChatCFD, a large language model-driven pipeline that automates CFD workflows within the OpenFOAM framework. It enables users to configure and execute complex simulations from natural language prompts or published literature with minimal expertise. The innovation is its structured approach to database construction, configuration validation, and error reflection, integrating CFD and OpenFOAM knowledge with general language models to improve accuracy and adaptability. Validation shows ChatCFD can autonomously reproduce published CFD results, handling complex, unseen configurations beyond basic examples, a task challenging for general language models.

Problem

• Automates CFD workflows in OpenFOAM via natural language
• Reduces expertise needed for complex CFD simulations
• Validates configurations and reflects errors autonomously

Innovation

• Automates CFD workflows using large language models
• Integrates OpenFOAM knowledge for accurate simulations
• Validates configurations and reflects errors autonomously