ChronoLLM: Customizing Language Models for Physics-Based Simulation Code Generation
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 47 of its 115 references that are in the map. First posted on arXiv 19 Aug 2025.
Builds on
47 of 115 references.
References · 47
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
- 2021Evaluating Large Language Models Trained on Codecited by 8,320
- 2020Measuring Massive Multitask Language Understandingcited by 7,963
- 2020Scaling Laws for Neural Language Modelscited by 6,586
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
- 2021The Power of Scale for Parameter-Efficient Prompt Tuningcited by 3,795
- 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
35 more
- 2022Training Compute-Optimal Large Language Modelscited by 3,019
- 2022Emergent Abilities of Large Language Modelscited by 2,512
- 2023Code Llama: Open Foundation Models for Codecited by 2,139
- 2017Gradient Episodic Memory for Continual Learningcited by 1,898
- 2023Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generationcited by 1,391
- 2021BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-modelscited by 1,245
- 2023A Survey on Evaluation of Large Language Modelscited by 1,242
- 2024SimPO: Simple Preference Optimization with a Reference-Free Rewardcited by 963
- 2024Gemma: Open Models Based on Gemini Research and Technologycited by 916
- 2022Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learningcited by 896
- 2021Show Your Work: Scratchpads for Intermediate Computation with Language Modelscited by 886
- 2024DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Modelscited by 867
- 2023StarCoder: may the source be with you!cited by 799
- 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 689
- 2023Are Emergent Abilities of Large Language Models a Mirage?cited by 523
- 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 463
- 2020Fine-Tuning Pretrained Language Models: Weight Initializations, Data Orders, and Early Stoppingcited by 384
- 2022A Systematic Evaluation of Large Language Models of Codecited by 363
- 2023LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Modelscited by 324
- 2021PPT: Pre-trained Prompt Tuning for Few-shot Learningcited by 232
- 2023AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Modelscited by 171
- 2024CodeGemma: Open Code Models Based on Gemmacited by 150
- 2023Structured Chain-of-Thought Prompting for Code Generationcited by 138
- 2023Continual Pre-Training of Large Language Models: How to (re)warm your model?cited by 137
- 2023Few-shot Fine-tuning vs. In-context Learning: A Fair Comparison and Evaluationcited by 136
- 2024Understanding Emergent Abilities of Language Models from the Loss Perspectivecited by 94
- 2018ROUGE 2.0: Updated and Improved Measures for Evaluation of Summarization Taskscited by 67
- 2022Out of the BLEU: how should we assess quality of the Code Generation models?cited by 65
- 2023OceanGPT: A Large Language Model for Ocean Science Taskscited by 43
- 2022Clinical Prompt Learning with Frozen Language Modelscited by 19
- 2024OMPGPT: A Generative Pre-trained Transformer Model for OpenMPcited by 16
- 2024Hippocrates: An Open-Source Framework for Advancing Large Language Models in Healthcarecited by 15
- 2024MPIrigen: MPI Code Generation through Domain-Specific Language Modelscited by 5
- 2024C4Q: A Chatbot for Quantumcited by 3
- 2018SRDA: Generating Instance Segmentation Annotation Via Scanning, Reasoning And Domain Adaptationcited by 1
Built on by
Citing papers per year: 2025: 1; 2026: 2.
3 papers.