# Simulation Code Generation for Fluid Systems using Large Language Models: Benchmarking Models and Prompting Strategies

arXiv: https://arxiv.org/abs/2607.29389 · HTML: https://mlsanity.com/paper/2607.29389/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 58 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 21 of 21)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024)
- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [QUIK: Towards End-to-End 4-Bit Inference on Generative Large Language Models](https://mlsanity.com/paper/2310.09259/) (2023)
- [Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications](https://mlsanity.com/paper/2503.01245/) (2025)
- [Devstral: Fine-tuning Language Models for Coding Agent Applications](https://mlsanity.com/paper/2509.25193/) (2025)
- [Fine-tuning a Large Language Model for Automating Computational Fluid Dynamics Simulations](https://mlsanity.com/paper/2504.09602/) (2025)
- [GraphCodeAgent: Dual Graph-Guided LLM Agent for Retrieval-Augmented Repo-Level Code Generation](https://mlsanity.com/paper/2504.10046/) (2025)
- [LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins](https://mlsanity.com/paper/2405.18092/) (2024)
- [SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models](https://mlsanity.com/paper/2506.15695/) (2025)
- [Source Code Clone Detection Using Unsupervised Similarity Measures](https://mlsanity.com/paper/2401.09885/) (2024)
- [From Engineering Diagrams to Graphs: Digitizing P&IDs with Transformers](https://mlsanity.com/paper/2411.13929/) (2024)
- [Text2Model: Generating dynamic chemical reactor models using large language models (LLMs)](https://mlsanity.com/paper/2503.17004/) (2025)
- [ModiGen: A Large Language Model-Based Workflow for Multi-Task Modelica Code Generation](https://mlsanity.com/paper/2503.18460/) (2025)
- [Are LLMs Reliable Code Reviewers? Systematic Overcorrection in Requirement Conformance Judgement](https://mlsanity.com/paper/2603.00539/) (2026)
- [A Survey on the Evaluation of Clone Detection Performance and Benchmarking](https://mlsanity.com/paper/2006.15682/) (2020)

## Built on by (most cited first, 1 of 1)

- [Beyond Executable Models: The Pufibara Agent Harness and the Modelica Agent Workflow Benchmark for Physical System Modeling](https://mlsanity.com/paper/2608.23653/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have demonstrated a strong ability to generate syntactically correct code from natural-language specifications. In this study, we explore how LLMs can be harnessed to automatically translate a neutral graph representation of fluid system models into executable code for two widely adopted simulation environments: the Python library WNTR and the Modelica Standard Library. We conduct a systematic comparison of ten state-of-the-art LLMs and six prompting strategies that differ in the contextual information supplied (e.g., code or documentation). For each configuration we assess the generated code using a suite of software-quality metrics and we validate the functional fidelity of the resulting simulation models by reproducing benchmark fluid system scenarios. Our findings offer concrete guidance for researchers and engineers seeking to integrate LLM-driven code synthesis into model-based design pipelines. While the best-performing configurations achieve acceptable syntactic quality, we observe substantial gaps remain in simulation fidelity.