LLMs show promise for fluid system simulation code generation, but fidelity gaps remain

A new arXiv paper explores the use of large language models (LLMs) for generating simulation code for fluid systems. Researchers compared ten state-of-the-art LLMs and six prompting strategies, evaluating the generated code using software-quality metrics and validating functional fidelity against benchmark fluid system scenarios. While the best configurations produced syntactically correct code, significant gaps remain in simulation fidelity, offering guidance for integrating LLM-driven code synthesis into design pipelines. AI

IMPACT LLMs show potential for automating simulation code generation, but further development is needed to ensure functional fidelity in complex systems.

RANK_REASON The cluster contains a research paper detailing experiments and findings on LLM capabilities for code generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• CatalyzeX Code Finder for Papers
• DagsHub
• Gotit.pub
• Hugging Face
• IArxiv
• Jan Marius Stürmer
• Modelica Standard Library
• ScienceCast
• WNTR

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →