mlsanityData to 13 Oct 2026

MetaOpenFOAM 2.0: Large Language Model Driven Chain of Thought for Automating CFD Simulation and Post-Processing

arXiv 2502.00498 ↗First posted 1 Feb 2025cs.AI physics.comp-phcited by 13

On the map: LLM reasoning → Spatial and embodied reasoning

Abstract (arXiv)

Computational Fluid Dynamics (CFD) is widely used in aerospace, energy, and biology to model fluid flow, heat transfer, and chemical reactions. While Large Language Models (LLMs) have transformed various domains, their application in CFD remains limited, particularly for complex tasks like post-processing. To bridge this gap, we introduce MetaOpenFOAM 2.0, which leverages Chain of Thought (COT) decomposition and iterative verification to enhance accessibility for non-expert users through natural language inputs. Tested on a new benchmark covering simulation (fluid flow, heat transfer, combustion) and post-processing (extraction, visualization), MetaOpenFOAM 2.0 achieved an Executability score of 6.3/7 and a pass rate of 86.9%, significantly outperforming MetaOpenFOAM 1.0 (2.1/7, 0%). Additionally, it proved cost-efficient, averaging 0.15 per case. An ablation study confirmed that COT-driven decomposition and iterative refinement substantially improved task performance. Furthermore, scaling laws showed that increasing COT steps enhanced accuracy while raising token usage, aligning with LLM post-training scaling trends. These results highlight the transformative potential of LLMs in automating CFD workflows for industrial and research applications. Code is available at https://github.com/Terry-cyx/MetaOpenFOAM

Key facts. Cited by 13 papers in the map (data through 13 Oct 2026). Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning. Builds on 16 of its 23 references that are in the map. First posted on arXiv 1 Feb 2025.

Builds on

16 of 23 references.

References · 16

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,376
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,205
  3. 2020Scaling Laws for Neural Language Modelscited by 6,494
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,657
  5. 2024Qwen2.5 Technical Reportcited by 4,840
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,218
  7. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,777
  8. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,758
  9. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,404
  10. 2023Self-collaboration Code Generation via ChatGPTcited by 257
  11. 2023Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaborationcited by 249
  12. 2023Playing repeated games with Large Language Modelscited by 216
4 more
  1. 2023Active Prompting with Chain-of-Thought for Large Language Modelscited by 154
  2. 2024Making Reasoning Matter: Measuring and Improving Faithfulness of Chain-of-Thought Reasoningcited by 109
  3. 2024Scaling Laws for Precisioncited by 94
  4. 2024MetaOpenFOAM: an LLM-based multi-agent framework for CFDcited by 39

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 6; 2026: 7.

13 papers.

Sort:

By area:

  1. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarioscited by 26
  2. 2025Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulationscited by 18
  3. 2025MooseAgent: A LLM Based Multi-agent Framework for Automating Moose Simulationcited by 17
  4. 2025ChatCFD: An LLM-Driven Agent for End-to-End CFD Automation with Structured Knowledge and Reasoningcited by 9
  5. 2025OptMetaOpenFOAM: Large Language Model Driven Chain of Thought for Sensitivity Analysis and Parameter Optimization based on CFDcited by 6
  6. 2026Agentic Scientific Simulation: Execution-Grounded Model Construction and Reconstructioncited by 4
  7. 2026Towards LLM-enabled autonomous combustion research: A literature-aware agent for self-corrective modeling workflowscited by 3
  8. 2026SwarmFoam: An OpenFOAM Multi-Agent System Based on Multiple Types of Large Language Modelscited by 3
  9. 2026AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agentscited by 3
  10. 2025CFD-copilot: leveraging domain-adapted large language model and model context protocol to enhance simulation automationcited by 1
  11. 2026PhyNiKCE: A Neurosymbolic Agentic Framework for Autonomous Computational Fluid Dynamicscited by 1
  12. 2026Large language models for partial differential equation workflowscited by 0
1 more
  1. 2026A Case-Bundle Operating Model for Coding Agents in OpenFOAM-Based CFDcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
  2. 2026AutoFOAM: The Self-Refining Autonomous OpenFOAM Agent
  3. 2025Foam-Agent: A Large Language Model-Based Multi-Agent Framework for Automating Computational Fluid Dynamics Workflows
  4. 2025Foam-Agent 2.0: An End-to-End Composable Multi-Agent Framework for Automating CFD Simulation in OpenFOAM
  5. 2024FLUID-LLM: Learning Computational Fluid Dynamics with Spatiotemporal-aware Large Language Models
  6. 2026A unified foundational framework for knowledge injection and evaluation of Large Language Models in Combustion Science
  7. 2024LLM Agent for Fire Dynamics Simulations
  8. 2026OMNIFLOW: A Physics-Grounded Multimodal Agent for Generalized Scientific Reasoning