让AI自主设计并优化流体仿真，无需人工干预。
AutoFOAM: The Self-Refining Autonomous OpenFOAM Agent
- 基于自然语言指令自动生成、运行和迭代流体模拟
- 在7个求解器上实现90%以上任务成功率，支持自动网格参数化
- 适合工程初学者和快速原型设计人员使用
计算流体动力学（CFD）在现代工程中至关重要，但使用开源求解器如OpenFOAM需大量专业知识和繁琐的配置。为降低门槛，我们提出AutoFOAM——一个自我演化的大型语言模型（LLM）代理，仅凭自然语言指令即可自主创建、评估、运行并演化OpenFOAM仿真。模型基于Qwen-coder 2.5-14B预训练，再在252条文本提示上微调，涵盖7个OpenFOAM求解器、13种参数化网格模板及y+感知数值策略。算法核心是包含7个阶段的复杂演化循环。为防止反复自训练导致模型退化，代理采用三种互补防崩溃机制：RAG增强重试上下文、字典级手术式修补、提示多样性改写。通过连接生成式AI与严谨流体模拟，AutoFOAM加速了快速原型设计，推动了先进CFD流程的普及。
原文摘要 · Abstract (English)
Computational Fluid Dynamics (CFD) plays an important role in modern engineering, but using open-source solvers such as OpenFOAM requires considerable knowledge and skills, as well as time-consuming configuration file setup. To reduce this burden, we propose AutoFOAM - a self-evolving large language model (LLM) agent that creates, evaluates, runs, and evolves its own OpenFOAM simulations based solely on natural-language instructions. Our model is pre-trained on the Qwen-coder 2.5-14B, which is then fine-tuned on 252 text prompts targeting 7 OpenFOAM solvers, 13 parametrized mesh templates, and a y plus-aware numerical policy. The crucial element of the algorithm is a sophisticated evolution loop composed of 7 stages. To prevent model degeneration under repeated self-training, the agent employs three complementary anti-collapse streams: RAG-augmented retry context, surgical dictionary-level patching, and prompt-diversity paraphrasing. By bridging generative artificial intelligence with rigorous fluid simulations, AutoFOAM accelerates rapid prototyping and democratizes advanced CFD workflows.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。