让大模型学会写物理仿真代码，帮专家快速上手工具
ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation
- 用特定流程微调大模型，使其能生成符合PyChrono规范的仿真脚本
- 生成脚本从单摆到车辆在变形地形上的复杂实验均可胜任
- 适合仿真领域新手，也可辅助专家快速验证建模思路
本文探讨预训练大语言模型能否被优化定制，成为帮助专家高效使用仿真工具的虚拟助手。以开源多体系统动力学引擎PyChrono为案例，提出一套框架，对开源与闭源大模型进行微调和定制，实现生成高质量的PyChrono仿真脚本。这些脚本涵盖从简单单摆到复杂车辆在可变形地形上运行的多种虚拟实验。虽然生成结果通常不完美，但往往可作为用户进一步修改的优质起点。此外，模型还能回答具体API问题或推荐建模方案。该框架具备通用性，可降低其他应用领域仿真工具的使用门槛。
原文摘要 · Abstract (English)
This contribution is concerned with the following issue: can pretrained large language models (LLMs) be refined and customized to the point where they become virtual assistants helping experts with the effective use of a simulation tool? In this case study, the ``simulation tool'' considered is PyChrono, an open source multi-physics dynamics engine for multibody systems. We present a framework for refining and customizing both open- and closed-source LLMs to harness the power of AI in generating scripts that perform PyChrono virtual experiments. We refine and customize several classes of LLMs through a process that leads to a quantifiable improvement in the quality of the generated PyChrono simulation scripts. These scripts can range from simple single-pendulum simulations to complex virtual experiments involving full vehicles on deformable terrain. While the generated scripts are rarely perfect, they often serve as strong starting points for the user to modify and improve on. Additionally, the LLM can answer specific API questions about the simulator, or recommend modeling approaches. The framework discussed is general and can be applied to lower the entry barrier for simulation tools associated with other application domains.
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。