ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Jingquan, Negrut, Andrew, Zhang, Harry, Slaton, Khailanii, Wang, Shu, Serban, Radu, Wu, Jinlong, Negrut, Dan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913997848051712
author Wang, Jingquan
Negrut, Andrew
Zhang, Harry
Slaton, Khailanii
Wang, Shu
Serban, Radu
Wu, Jinlong
Negrut, Dan
author_facet Wang, Jingquan
Negrut, Andrew
Zhang, Harry
Slaton, Khailanii
Wang, Shu
Serban, Radu
Wu, Jinlong
Negrut, Dan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2508_13975
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation
Wang, Jingquan
Negrut, Andrew
Zhang, Harry
Slaton, Khailanii
Wang, Shu
Serban, Radu
Wu, Jinlong
Negrut, Dan
Artificial Intelligence
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.
title ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation
topic Artificial Intelligence
url https://arxiv.org/abs/2508.13975