SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models

• URL: http://arxiv.org/abs/2506.15695v1
• Date: Wed, 28 May 2025 00:35:43 GMT
• Title: SimuGen: Multi-modal Agentic Framework for Constructing Block Diagram-Based Simulation Models
• Authors: Xinxing Ren, Qianbo Zang, Zekun Guo,
• Abstract summary: SimuGen is a framework that automatically generates accurate Simulink simulation code by leveraging both the visual Simulink diagram and domain knowledge.<n>Our source code is publicly available at https://github.com/renxinxing123/SimuGen_beta.
• Score: 0.07315096254838022
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Bridging Literature and the Universe Via A Multi-Agent Large Language Model System [5.935305898559785]
  Physicists face the challenge of searching through vast amounts of literature to extract simulation parameters from dense academic papers.<n>We introduce SimAgents, a multi-agent system designed to automate both parameter configuration from the literature and preliminary analysis for cosmology research.<n>SimAgents is powered by specialized LLM agents capable of physics reasoning, simulation software validation, and tool execution.
  arXiv  Detail & Related papers  (2025-07-11T18:31:20Z)
• G-Sim: Generative Simulations with Large Language Models and Gradient-Free Calibration [48.948187359727996]
  G-Sim is a hybrid framework that automates simulator construction with rigorous empirical calibration.<n>It produces reliable, causally-informed simulators, mitigating data-inefficiency and enabling robust system-level interventions.
  arXiv  Detail & Related papers  (2025-06-10T22:14:34Z)
• YuLan-OneSim: Towards the Next Generation of Social Simulator with Large Language Models [50.86336063222539]
  We introduce a novel social simulator called YuLan-OneSim.<n>Users can simply describe and refine their simulation scenarios through natural language interactions with our simulator.<n>We implement 50 default simulation scenarios spanning 8 domains, including economics, sociology, politics, psychology, organization, demographics, law, and communication.
  arXiv  Detail & Related papers  (2025-05-12T14:05:17Z)
• Experiments with Large Language Models on Retrieval-Augmented Generation for Closed-Source Simulation Software [0.36832029288386137]
  Retrieval-Augmented Generation (RAG) might yield a solution for knowledge-intensive tasks.<n>This paper explores the application of RAG to closed-source simulation software.
  arXiv  Detail & Related papers  (2025-02-06T09:48:04Z)
• Synthesizing Post-Training Data for LLMs through Multi-Agent Simulation [51.20656279478878]
  MATRIX is a multi-agent simulator that automatically generates diverse text-based scenarios.<n>We introduce MATRIX-Gen for controllable and highly realistic data synthesis.<n>On AlpacaEval 2 and Arena-Hard benchmarks, Llama-3-8B-Base, post-trained on datasets synthesized by MATRIX-Gen with just 20K instruction-response pairs, outperforms Meta's Llama-3-8B-Instruct model.
  arXiv  Detail & Related papers  (2024-10-18T08:01:39Z)
• GenSim: A General Social Simulation Platform with Large Language Model based Agents [111.00666003559324]
  We propose a novel large language model (LLMs)-based simulation platform called textitGenSim. Our platform supports one hundred thousand agents to better simulate large-scale populations in real-world contexts. To our knowledge, GenSim represents an initial step toward a general, large-scale, and correctable social simulation platform.
  arXiv  Detail & Related papers  (2024-10-06T05:02:23Z)
• FactorSim: Generative Simulation via Factorized Representation [14.849320460718591]
  We introduce FACTORSIM that generates full simulations in code from language input that can be used to train agents. For evaluation, we introduce a generative simulation benchmark that assesses the generated simulation code's accuracy and effectiveness in facilitating zero-shot transfers in reinforcement learning settings. We show that FACTORSIM outperforms existing methods in generating simulations regarding prompt alignment (e.g., accuracy), zero-shot transfer abilities, and human evaluation.
  arXiv  Detail & Related papers  (2024-09-26T09:00:30Z)
• Promptable Closed-loop Traffic Simulation [57.36568236100507]
  ProSim is a multimodal promptable closed-loop traffic simulation framework. ProSim rolls out a traffic scenario in a closed-loop manner, modeling each agent's interaction with other traffic participants. To support research on promptable traffic simulation, we create ProSim-Instruct-520k, a multimodal prompt-scenario paired driving dataset.
  arXiv  Detail & Related papers  (2024-09-09T17:59:15Z)
• Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research [76.93956925360638]
  Waymax is a new data-driven simulator for autonomous driving in multi-agent scenes. It runs entirely on hardware accelerators such as TPUs/GPUs and supports in-graph simulation for training. We benchmark a suite of popular imitation and reinforcement learning algorithms with ablation studies on different design decisions.
  arXiv  Detail & Related papers  (2023-10-12T20:49:15Z)
• Simulation of an Elevator Group Control Using Generative Adversarial Networks and Related AI Tools [0.6481500397175589]
  Generative Adversarial Networks (GANs) are powerful tools for generating new data for a variety of tasks. This article investigates the applicability of GANs for imitating simulations.
  arXiv  Detail & Related papers  (2020-09-03T14:22:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.