SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models
This addresses a domain-specific problem for engineers and researchers using Simulink models, representing an incremental improvement by integrating multimodal inputs and specialized agents.
The paper tackles the challenge of LLMs struggling to generate reliable Simulink simulation code from text-only inputs by proposing SimuGen, a multimodal agent-based framework that leverages visual diagrams and domain knowledge to automatically produce accurate Simulink code, with the source code made publicly available.
Recent advances in large language models (LLMs) have shown impressive performance in mathematical reasoning and code generation. However, LLMs still struggle in the simulation domain, particularly in generating Simulink models, which are essential tools in engineering and scientific research. Our preliminary experiments indicate that LLM agents often fail to produce reliable and complete Simulink simulation code from text-only inputs, likely due to the lack of Simulink-specific data in their pretraining. To address this challenge, we propose SimuGen, a multimodal agent-based framework that automatically generates accurate Simulink simulation code by leveraging both the visual Simulink diagram and domain knowledge. SimuGen coordinates several specialized agents, including an investigator, unit test reviewer, code generator, executor, debug locator, and report writer, supported by a domain-specific knowledge base. This collaborative and modular design enables interpretable, robust, and reproducible Simulink simulation generation. Our source code is publicly available at https://github.com/renxinxing123/SimuGen_beta.