标题： MetaOpenFOAM 2.0：用于自动化CFD模拟和后处理的大语言模型驱动的思维链 显示英文标题

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

摘要： 计算流体动力学（CFD）在航空航天、能源和生物学中被广泛用于模拟流体流动、传热和化学反应。 尽管大型语言模型（LLMs）已改变了多个领域，但其在CFD中的应用仍然有限，特别是在复杂的任务如后处理方面。 为了弥补这一差距，我们引入了MetaOpenFOAM 2.0，它利用思维链（COT）分解和迭代验证，通过自然语言输入提高非专家用户的可访问性。 在涵盖模拟（流体流动、传热、燃烧）和后处理（提取、可视化）的新基准测试中，MetaOpenFOAM 2.0取得了6.3/7的可执行性分数和86.9%的通过率，显著优于MetaOpenFOAM 1.0（2.1/7，0%）。 此外，它证明了成本效益，平均每案例0.15美元。 消融研究证实，COT驱动的分解和迭代优化显著提高了任务性能。 此外，尺度定律显示增加COT步骤可以提高准确性，同时增加令牌使用量，这与LLM后训练的尺度趋势一致。 这些结果突显了LLMs在自动化CFD工作流程方面的变革潜力，适用于工业和研究应用。 代码可在https://github.com/Terry-cyx/MetaOpenFOAM获取。 显示英文摘要

摘要： 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