计算机仿真为探索各学科的复杂系统提供了一套强大的工具集。该领域中一种极具影响力的方法是基于智能体的建模(Agent-Based Modeling,ABM),它利用单个智能体的交互来模拟复杂的系统动力学。ABM的优势在于其自下而上的方法论,通过对系统单个组件的行为建模来揭示涌现现象。然而,ABM也有自身的一系列挑战,尤其是难以在数学方程或规则中对自然语言指令和常识进行建模。本文旨在通过将GPT等大语言模型(Large Language Models,LLMs)集成到ABM中来突破这些局限,这种融合催生了一个新颖的框架——Smart Agent-Based Modeling(SABM)。基于智能体(以智能性、适应性和计算能力为特征的实体)的概念,我们探索了利用LLM驱动的智能体以更细腻、更真实的方式模拟现实场景的方向。在这项全面的探索中,我们阐明了ABM的最新进展,介绍了SABM的潜力和方法论,并展示了三个案例研究(源代码可在https://github.com/Roihn/SABM获取),以论证SABM方法论并验证其在现实系统建模中的有效性。此外,我们还展望了SABM未来的多个方面,预期其应用前景将更为广阔。通过这项工作,我们旨在重新定义计算机仿真的边界,实现对复杂系统更深刻的理解。
英文摘要:
Computer simulations offer a robust toolset for exploring complex systems across various disciplines. A particularly impactful approach within this realm is Agent-Based Modeling (ABM), which harnesses the interactions of individual agents to emulate intricate system dynamics. ABM's strength lies in its bottom-up methodology, illuminating emergent phenomena by modeling the behaviors of individual components of a system. Yet, ABM has its own set of challenges, notably its struggle with modeling natural language instructions and common sense in mathematical equations or rules. This paper seeks to transcend these boundaries by integrating Large Language Models (LLMs) like GPT into ABM. This amalgamation gives birth to a novel framework, Smart Agent-Based Modeling (SABM). Building upon the concept of smart agents -- entities characterized by their intelligence, adaptability, and computation ability -- we explore in the direction of utilizing LLM-powered agents to simulate real-world scenarios with increased nuance and realism. In this comprehensive exploration, we elucidate the state of the art of ABM, introduce SABM's potential and methodology, and present three case studies (source codes available at https://github.com/Roihn/SABM), demonstrating the SABM methodology and validating its effectiveness in modeling real-world systems. Furthermore, we cast a vision towards several aspects of the future of SABM, anticipating a broader horizon for its applications. Through this endeavor, we aspire to redefine the boundaries of computer simulations, enabling a more profound understanding of complex systems.
Systemic approach for modeling a generic smart grid
Laboratory LI-PaRAD University of Versailles Versailles France;Pole Universitaire L\'eonard de Vinci De Vinci Research Center La D\'efense France;Laboratory LI-PaRAD;Pole Universitaire L\'eonard de Vinci De Vinci Research Center
Artificial Intelligence for Sustainability: Facilitating Sustainable Smart Product-Service Systems with Computer Vision
Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院);University of Bayreuth(拜罗伊特大学);University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Plansee SE(攀时股份公司)
Fuzzy temporal convolutional neural networks in P300-based Brain-computer interface for smart home interaction
Universidad de Ingeniería y Tecnología - UTEC(工程与技术大学(UTEC));University of Campinas(坎皮纳斯大学);University of Essex(埃塞克斯大学);Nantong University(南通大学);University of Jaen(哈恩大学)
Smart Help: Strategic Opponent Modeling for Proactive and Adaptive Robot Assistance in Households
Beijing Institute for General Artificial Intelligence (BIGAI)(北京通用人工智能研究院);State Key Laboratory of General Artificial Intelligence(通用人工智能国家重点实验室);Tsinghua University(清华大学);Peking University(北京大学);University of California, Los Angeles(加州大学洛杉矶分校)
Heads Up eXperience (HUX): Always-On AI Companion for Human Computer Environment Interaction
Vellore Institute of Technology - Chennai(韦洛尔理工大学 Chennai校区);Shiv Nadar University - Chennai(希夫纳达尔大学 Chennai校区);Indian Institute of Technology - Kanpur(坎普尔印度理工学院)
本文提出 HUX AI 系统,通过追踪眼动、分析环境与解读语音实现多模态数据增强,旨在扩展现实环境中作为常驻 AI 伴侣,弥合数字与物理交互差距,革新人机协作。
From Automation to Autonomy in Smart Manufacturing: A Bayesian Optimization Framework for Modeling Multi-Objective Experimentation and Sequential Decision Making
Bangladesh University of Engineering and Technology(孟加拉工程技术大学);West Virginia University(西弗吉尼亚大学)