SOCIA: An End-to-End Agentic Framework for Automated Cyber-Physical-Social Simulator Generation

• URL: http://arxiv.org/abs/2505.12006v2
• Date: Fri, 23 May 2025 15:30:42 GMT
• Title: SOCIA: An End-to-End Agentic Framework for Automated Cyber-Physical-Social Simulator Generation
• Authors: Yuncheng Hua, Ji Miao, Mehdi Jafari, Jianxiang Xie, Hao Xue, Flora D. Salim,
• Abstract summary: SOCIA (Simulation Orchestration for Cyber-physical-social Intelligence and Agents) is a novel end-to-end framework leveraging Large Language Model (LLM)-based multi-agent systems.<n>It automates the generation of high-fidelity Cyber-Physical-Social (CPS) simulators.
• Score: 9.689635475090085
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper introduces SOCIA (Simulation Orchestration for Cyber-physical-social Intelligence and Agents), a novel end-to-end framework leveraging Large Language Model (LLM)-based multi-agent systems to automate the generation of high-fidelity Cyber-Physical-Social (CPS) simulators. Addressing the challenges of labor-intensive manual simulator development and complex data calibration, SOCIA integrates a centralized orchestration manager that coordinates specialized agents for tasks including data comprehension, code generation, simulation execution, and iterative evaluation-feedback loops. Through empirical evaluations across diverse CPS tasks, such as mask adoption behavior simulation (social), personal mobility generation (physical), and user modeling (cyber), SOCIA demonstrates its ability to produce high-fidelity, scalable simulations with reduced human intervention. These results highlight SOCIA's potential to offer a scalable solution for studying complex CPS phenomena

Related papers

• Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative Approaches [76.12691010182802]
  This survey focuses on enabling agentic artificial intelligence (AI) in satellite-augmented low-altitude economy and terrestrial networks (SLAETNs)<n>We introduce the architecture and characteristics of SLAETNs, and analyze the challenges that arise in integrating satellite, aerial, and terrestrial components.<n>We examine how these models empower agentic functions across three domains: communication enhancement, security and privacy protection, and intelligent satellite tasks.
  arXiv  Detail & Related papers  (2025-07-19T14:07:05Z)
• 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)
• User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation [38.48048183731099]
  User simulation is an emerging interdisciplinary topic with multiple critical applications in the era of Generative AI.<n>It involves creating an intelligent agent that mimics the actions of a human user interacting with an AI system.<n>User simulation has profound implications for diverse fields and plays a vital role in the pursuit of Artificial General Intelligence.
  arXiv  Detail & Related papers  (2025-01-08T10:49:13Z)
• GausSim: Foreseeing Reality by Gaussian Simulator for Elastic Objects [55.02281855589641]
  GausSim is a novel neural network-based simulator designed to capture the dynamic behaviors of real-world elastic objects represented through Gaussian kernels.<n>We leverage continuum mechanics and treat each kernel as a Center of Mass System (CMS) that represents continuous piece of matter.<n>In addition, GausSim incorporates explicit physics constraints, such as mass and momentum conservation, ensuring interpretable results and robust, physically plausible simulations.
  arXiv  Detail & Related papers  (2024-12-23T18:58:17Z)
• 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)
• Graph-based Modeling and Simulation of Emergency Services Communication Systems [0.0]
  Emergency Services Communication Systems (ESCS) are evolving into Internet Protocol based communication networks. This paper introduces a robust, adaptable graph-based simulation framework and essential mathematical models for ESCS simulation.
  arXiv  Detail & Related papers  (2024-09-03T12:53:35Z)
• ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems [80.69865295743149]
  This work attempts to study using LLM-based agents to design collaborative AI systems autonomously.<n>Based on ComfyBench, we develop ComfyAgent, a framework that empowers agents to autonomously design collaborative AI systems by generating.<n>While ComfyAgent achieves a comparable resolve rate to o1-preview and significantly surpasses other agents on ComfyBench, ComfyAgent has resolved only 15% of creative tasks.
  arXiv  Detail & Related papers  (2024-09-02T17:44:10Z)
• Large Language Model-based Human-Agent Collaboration for Complex Task Solving [94.3914058341565]
  We introduce the problem of Large Language Models (LLMs)-based human-agent collaboration for complex task-solving. We propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process.
  arXiv  Detail & Related papers  (2024-02-20T11:03:36Z)
• User Behavior Simulation with Large Language Model based Agents [116.74368915420065]
  We propose an LLM-based agent framework and design a sandbox environment to simulate real user behaviors. Based on extensive experiments, we find that the simulated behaviors of our method are very close to the ones of real humans.
  arXiv  Detail & Related papers  (2023-06-05T02:58:35Z)
• Active Predicting Coding: Brain-Inspired Reinforcement Learning for Sparse Reward Robotic Control Problems [79.07468367923619]
  We propose a backpropagation-free approach to robotic control through the neuro-cognitive computational framework of neural generative coding (NGC) We design an agent built completely from powerful predictive coding/processing circuits that facilitate dynamic, online learning from sparse rewards. We show that our proposed ActPC agent performs well in the face of sparse (extrinsic) reward signals and is competitive with or outperforms several powerful backprop-based RL approaches.
  arXiv  Detail & Related papers  (2022-09-19T16:49:32Z)
• Automated Adversary Emulation for Cyber-Physical Systems via Reinforcement Learning [4.763175424744536]
  We develop an automated, domain-aware approach to adversary emulation for cyber-physical systems. We formulate a Markov Decision Process (MDP) model to determine an optimal attack sequence over a hybrid attack graph. We apply model-based and model-free reinforcement learning (RL) methods to solve the discrete-continuous MDP in a tractable fashion.
  arXiv  Detail & Related papers  (2020-11-09T18:44:29Z)

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.