mlsanityData to 14 Oct 2026

A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek

arXiv 2504.02888 ↗First posted 2 Apr 2025cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

We evaluated the performance of OpenFOAMGPT incorporating multiple large-language models. Some of the present models efficiently manage different CFD tasks such as adjusting boundary conditions, turbulence models, and solver configurations, although their token cost and stability vary. Locally deployed smaller models like QwQ-32B struggled with generating valid solver files for complex processes. Zero-shot prompting commonly failed in simulations with intricate settings, even for large models. Challenges with boundary conditions and solver keywords stress the requirement for expert supervision, indicating that further development is needed to fully automate specialized CFD simulations.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 18 of its 42 references that are in the map. First posted on arXiv 2 Apr 2025.

Builds on

18 of 42 references.

References · 18

  1. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,944
  2. 2022PaLM: Scaling Language Modeling with Pathwayscited by 5,326
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 463
  5. 2019Machine Learning for Fluid Mechanicscited by 385
  6. 2021Enhancing Computational Fluid Dynamics with Machine Learningcited by 138
  7. 2024A Review of Large Language Models and Autonomous Agents in Chemistrycited by 99
  8. 2024LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discoverycited by 86
  9. 2023Prompt a Robot to Walk with Large Language Modelscited by 45
  10. 2024MetaOpenFOAM: an LLM-based multi-agent framework for CFDcited by 39
  11. 2018Deep Neural Networks for Data-Driven Turbulence Modelscited by 35
  12. 2023The transformative potential of machine learning for experiments in fluid mechanicscited by 27
6 more
  1. 2023Pre-Trained Large Language Models for Industrial Controlcited by 16
  2. 2024Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Designcited by 9
  3. 2023Toward Discretization-Consistent Closure Schemes for Large Eddy Simulation Using Reinforcement Learningcited by 5
  4. 2024FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Modelscited by 5
  5. 2024Additive-feature-attribution methods: a review on explainable artificial intelligence for fluid dynamics and heat transfercited by 4
  6. 2024Training microrobots to swim by a large language modelcited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulationscited by 18
  2. 2026ALL-FEM: Agentic Large Language models Fine-tuned for Finite Element Methodscited by 12
  3. 2025CFD-copilot: leveraging domain-adapted large language model and model context protocol to enhance simulation automationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing
  2. 2025OptMetaOpenFOAM: Large Language Model Driven Chain of Thought for Sensitivity Analysis and Parameter Optimization based on CFD
  3. 2025ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Structured Knowledge and Reasoning
  4. 2025Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows
  5. 2026AutoFOAM: The Self-Refining Autonomous OpenFOAM Agent
  6. 2025Foam-Agent 2.0: An End-to-End Composable Multi-Agent Framework for Automating CFD Simulation in OpenFOAM
  7. 2026AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
  8. 2026Large language models for partial differential equation workflows