ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Domain-Specific Structured Reasoning

• URL: http://arxiv.org/abs/2506.02019v2
• Date: Mon, 08 Sep 2025 16:15:06 GMT
• Title: ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Domain-Specific Structured Reasoning
• Authors: E Fan, Kang Hu, Zhuowen Wu, Jiangyang Ge, Jiawei Miao, Yuzhi Zhang, He Sun, Weizong Wang, Tianhan Zhang,
• Abstract summary: ChatCFD is an automated agent system for OpenFOAM simulations.<n>Its four-stage pipeline enables iterative trial-reflection-refinement for intricate setups.<n>ChatCFD shows strong potential as a modular component in MCP-based agent networks for collaborative multi-agent systems.
• Score: 4.098524616768554
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Computational Fluid Dynamics (CFD) is essential for advancing scientific and engineering fields but is hindered by operational complexity, high expertise requirements, and limited accessibility. This paper introduces ChatCFD, an automated agent system for OpenFOAM simulations that processes multi-modal inputs (e.g., research papers, meshes) via an interactive interface, leveraging DeepSeek-R1 and DeepSeek-V3 large language models, a multi-agent architecture, and OpenFOAM knowledge. Its four-stage pipeline (Knowledge Base Construction, User Input Processing, Case File Generation, and Execution and Error Reflection) enables iterative trial-reflection-refinement for intricate setups, supporting diverse physical models and external meshes. Validation on 205 benchmark tutorial cases, 110 perturbed variants, and 2 literature-derived cases shows ChatCFD's 82.1 percent operational success rate on basic cases, outperforming MetaOpenFOAM (6.2 percent) and Foam-Agent (42.3 percent), and 60-80 percent on literature-derived complex cases. Turbulence model studies show a 40 percent success rate for common models versus 10 percent for rare ones like RNG k-epsilon. Physics coupling analyses reveal higher resource demands for multi-physics-coupled cases, while LLM bias toward simpler setups introduces persistent errors, such as dimensional inconsistency. Ablation studies highlight the efficacy of RAG-based modules and reflection mechanisms. By automating hypothesis testing and parameter exploration, ChatCFD accelerates scientific discovery in fluid mechanics and engineering, addressing LLM limitations through structured design and showing strong potential as a modular component in MCP-based agent networks for collaborative multi-agent systems, paving the way for scalable AI-driven CFD innovation. The code for ChatCFD is available at https://github.com/ConMoo/ChatCFD.

Related papers

• Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection [59.04089915447622]
  ForenAgent is an interactive IFD framework that enables MLLMs to autonomously generate, execute, and refine Python-based low-level tools around the detection objective.<n>Inspired by human reasoning, we design a dynamic reasoning loop comprising global perception, local focusing, iterative probing, and holistic adjudication.<n>Experiments show that ForenAgent exhibits emergent tool-use competence and reflective reasoning on challenging IFD tasks.
  arXiv  Detail & Related papers  (2025-12-18T08:38:44Z)
• CFD-copilot: leveraging domain-adapted large language model and model context protocol to enhance simulation automation [6.71937346130764]
  CFD-copilot is a framework designed to facilitate natural language-driven CFD simulation from setup to post-processing.<n>For post-processing, the framework utilizes the model context protocol (MCP), an open standard that decouples LLM reasoning from external tool execution.<n>The framework was evaluated on benchmarks including the NACA0012 airfoil and the three-element 30P-30N airfoil.
  arXiv  Detail & Related papers  (2025-12-08T11:42:32Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization [103.74675519953898]
  Long-chain reflective reasoning is a prerequisite for solving complex real-world problems.<n>We build a benchmark consisting 1,260 samples of 42 challenging synthetic tasks.<n>We generate post-training data and explore learning paradigms for exploiting such data.
  arXiv  Detail & Related papers  (2025-10-09T17:53:58Z)
• A Lightweight Large Language Model-Based Multi-Agent System for 2D Frame Structural Analysis [21.13581042992661]
  Large language models (LLMs) have recently been used to empower autonomous agents in engineering.<n>This paper develops a LLM-based multi-agent system to automate finite element modeling of 2D frames.<n>The system achieves accuracy over 80% in most cases across 10 repeated trials, outperforming Gemini-2.5 Pro and ChatGPT-4o models.
  arXiv  Detail & Related papers  (2025-10-06T22:12:52Z)
• Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs [78.09559830840595]
  We present the first systematic study on quantizing diffusion-based language models.<n>We identify the presence of activation outliers, characterized by abnormally large activation values.<n>We implement state-of-the-art PTQ methods and conduct a comprehensive evaluation.
  arXiv  Detail & Related papers  (2025-08-20T17:59:51Z)
• Re:Form -- Reducing Human Priors in Scalable Formal Software Verification with RL in LLMs: A Preliminary Study on Dafny [68.00108157244952]
  Large Language Models (LLMs) trained with Reinforcement Learning (RL) face a significant challenge: their verification processes are neither reliable nor scalable.<n>A promising yet largely uncharted alternative is formal language-based reasoning.<n>Grounding LLMs in rigorous formal systems where generative models operate in formal language spaces (e.g., Dafny) enables the automatic and mathematically provable verification of their reasoning processes and outcomes.
  arXiv  Detail & Related papers  (2025-07-22T08:13:01Z)
• Foam-Agent: Towards Automated Intelligent CFD Workflows [2.303486126296845]
  We present Foam-Agent, a multi-agent framework that automates complex OpenFOAM-based CFD simulation from natural language inputs.<n>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.
  arXiv  Detail & Related papers  (2025-05-08T07:05:51Z)
• A Domain Adaptation of Large Language Models for Classifying Mechanical Assembly Components [0.9134277125744795]
  Functional modeling enables designers to reason about product functions before specific structural details are determined.<n>The effectiveness of function-based design is often hindered by the lack of well-structured and comprehensive functional data.<n>This study proposes a novel LLM-based domain adaptation (DA) framework using fine-tuning for the automated classification of mechanical assembly parts' functions.
  arXiv  Detail & Related papers  (2025-05-02T23:32:50Z)
• Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations [11.902947290205645]
  Large language models (LLMs) have advanced scientific computing, their use in CFD is automating.<n>We introduce a novel approach centered on domain-specific LLM adaptation.<n>A multi-agent framework orchestrates the process, autonomously verifying inputs, generating configurations, running simulations, and correcting errors.
  arXiv  Detail & Related papers  (2025-04-13T14:35:30Z)
• A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek [26.280882787841204]
  We evaluated the performance of OpenFOAMGPT incorporating multiple large-language models.<n>Some of the present models efficiently manage different CFD tasks such as adjusting boundary conditions.<n>Smaller models like QwQ-32B struggled with generating valid solver files for complex processes.
  arXiv  Detail & Related papers  (2025-04-02T14:04:52Z)
• Flex: End-to-End Text-Instructed Visual Navigation from Foundation Model Features [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies.<n>Our findings are synthesized in Flex (Fly lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors.<n>We demonstrate the effectiveness of this approach on a quadrotor fly-to-target task, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models [79.41139393080736]
  Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and. Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting. LLMs to downstream tasks. We propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning.
  arXiv  Detail & Related papers  (2024-09-30T10:48:20Z)
• A Large Language Model and Denoising Diffusion Framework for Targeted Design of Microstructures with Commands in Natural Language [0.0]
  We propose a framework that integrates Natural Language Processing (NLP), Large Language Models (LLMs), and Denoising Diffusion Probabilistic Models (DDPMs) Our framework employs contextual data augmentation, driven by a pretrained LLM, to generate and expand a diverse dataset of microstructure descriptors. A retrained NER model extracts relevant microstructure descriptors from user-provided natural language inputs, which are then used by the DDPM to generate microstructures with targeted mechanical properties and topological features.
  arXiv  Detail & Related papers  (2024-09-22T14:45:22Z)
• FactorLLM: Factorizing Knowledge via Mixture of Experts for Large Language Models [50.331708897857574]
  We introduce FactorLLM, a novel approach that decomposes well-trained dense FFNs into sparse sub-networks without requiring any further modifications. FactorLLM achieves comparable performance to the source model securing up to 85% model performance while obtaining over a 30% increase in inference speed.
  arXiv  Detail & Related papers  (2024-08-15T16:45:16Z)
• MetaOpenFOAM: an LLM-based multi-agent framework for CFD [11.508919041921942]
  MetaOpenFOAM is a novel multi-agent collaborations framework. It aims to complete CFD simulation tasks with only natural language as input. It harnesses the power of MetaGPT's assembly line paradigm.
  arXiv  Detail & Related papers  (2024-07-31T04:01:08Z)
• CELA: Cost-Efficient Language Model Alignment for CTR Prediction [70.65910069412944]
  Click-Through Rate (CTR) prediction holds a paramount position in recommender systems.<n>Recent efforts have sought to mitigate these challenges by integrating Pre-trained Language Models (PLMs)<n>We propose textbfCost-textbfEfficient textbfLanguage Model textbfAlignment (textbfCELA) for CTR prediction.
  arXiv  Detail & Related papers  (2024-05-17T07:43:25Z)
• On Conditional and Compositional Language Model Differentiable Prompting [75.76546041094436]
  Prompts have been shown to be an effective method to adapt a frozen Pretrained Language Model (PLM) to perform well on downstream tasks. We propose a new model, Prompt Production System (PRopS), which learns to transform task instructions or input metadata, into continuous prompts.
  arXiv  Detail & Related papers  (2023-07-04T02:47:42Z)
• SOLIS -- The MLOps journey from data acquisition to actionable insights [62.997667081978825]
  In this paper we present a unified deployment pipeline and freedom-to-operate approach that supports all requirements while using basic cross-platform tensor framework and script language engines. This approach however does not supply the needed procedures and pipelines for the actual deployment of machine learning capabilities in real production grade systems.
  arXiv  Detail & Related papers  (2021-12-22T14:45:37Z)
• GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures [57.46093180685175]
  We demonstrate a set of modifications to the structure of a Transformer layer, producing a more efficient architecture. We add a convolutional module to complement the self-attention module, decoupling the learning of local and global interactions. We apply the resulting architecture to language representation learning and demonstrate its superior performance compared to BERT models of different scales.
  arXiv  Detail & Related papers  (2021-06-10T15:41:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.