<ul><li>MooseAgent is an automated solution framework that uses large-scale pre-trained language models (LLMs) and a multi-agent system to automate the simulation process in the MOOSE framework.</li><li>It utilizes LLMs to understand user-described simulation requirements in natural language and generates MOOSE input files through task decomposition and iterative verification strategies.</li><li>MooseAgent improves accuracy and reduces model hallucinations by utilizing a vector database containing annotated MOOSE input cards and function documentation.</li><li>The framework shows promising results in automating the MOOSE simulation process, particularly for relatively simple single-physics problems.</li></ul>

MooseAgent: A LLM Based Multi-agent Framework for Automating Moose Simulation

Discover more