article · ArXiv.org · 2025
ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation
Jing‐Quan Wang, Andrew Negrut, Harry Zhang, Khailanii Slaton, Shunli Wang, Radu Serban, Jinlong Wu, Dan Negruţ
Cited by 0Open access
Abstract
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.
Cite this paper
Wang, J., Negrut, A., Zhang, H., Slaton, K., Wang, S., Serban, R., Wu, J., & Negruţ, D. (2025). ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation. ArXiv.org.
Wang, Jing‐Quan, et al. “ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation.” ArXiv.org, 2025.
Wang, Jing‐Quan, Andrew Negrut, Harry Zhang, Khailanii Slaton, Shunli Wang, Radu Serban, Jinlong Wu, and Dan Negruţ. 2025. “ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation.” ArXiv.org.
Wang, J. et al. (2025) ‘ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation’, ArXiv.org.
@article{wang2025chronollm,
title = {{ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation}},
author = {Wang, Jing‐Quan and Negrut, Andrew and Zhang, Harry and Slaton, Khailanii and Wang, Shunli and Serban, Radu and Wu, Jinlong and Negruţ, Dan},
journal = {ArXiv.org},
year = {2025}
}Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.