This paper presents a novel design of a multi-agent system framework that
applies a large language model (LLM) to automate the parametrization of process
simulations in digital twins. We propose a multi-agent framework that includes
four types of agents: observation, reasoning, decision and summarization. By
enabling dynamic interaction between LLM agents and simulation model, the
developed system can automatically explore the parametrization of the
simulation and use heuristic reasoning to determine a set of parameters to
control the simulation to achieve an objective. The proposed approach enhances
the simulation model by infusing it with heuristics from LLM and enables
autonomous search for feasible parametrization to solve a user task.
Furthermore, the system has the potential to increase user-friendliness and
reduce the cognitive load on human users by assisting in complex
decision-making processes. The effectiveness and functionality of the system
are demonstrated through a case study, and the visualized demos are available
at a GitHub Repository: this https URL

本文介绍了一种新颖的多智能体系统框架设计，利用大型语言模型（LLM）自动化数字孪生中的过程模拟参数化。我们提出了一个多智能体框架，包括观测、推理、决策和总结四种类型的智能体。通过启用 LLM 智能体与模拟模型之间的动态交互，该系统可以自动探索模拟的参数化，并使用启发式推理确定一组参数以控制模拟以实现目标。所提出的方法通过将 LLM 的启发式融入模拟模型，增强了模拟模型，并通过协助复杂的决策过程，增加了对用户的友好性并减轻了用户的认知负荷。通过案例研究证明了系统的有效性和功能，并在 GitHub 存储库中提供可视化演示。

模拟中的 LLM 实验：用于数字孪生中的过程仿真参数化的大型语言模型多主体系统

LLM experiments with simulation: Large Language Model Multi-Agent System  for Process Simulation Parametrization in Digital Twins

We propose a novel program of heuristic reasoning within artificial
intelligence (AI) systems. Through a series of innovative experiments,
including variations of the classic Linda problem and a novel application of
the Beauty Contest game, we uncover trade-offs between accuracy maximization
and effort reduction that shape the conditions under which AIs transition
between exhaustive logical processing and the use of cognitive shortcuts
(heuristics). We distinguish between the 'instrumental' use of heuristics to
match resources with objectives, and 'mimetic absorption,' whereby heuristics
are learned from humans, and manifest randomly and universally. We provide
evidence that AI, despite lacking intrinsic goals or self-awareness, manifests
an adaptive balancing of precision and efficiency, consistent with principles
of resource-rational human cognition as explicated in classical theories of
bounded rationality and dual-process theory.

我们提出了一种新颖的启发式推理方案，通过一系列创新性实验，包括经典的 Linda 问题的变形和对美丽比赛游戏的新颖应用，我们揭示了准确性最大化和努力减少之间的权衡，这决定了 AI 在穷尽逻辑处理和使用认知捷径（启发式）之间转换的条件。我们区分了启发式的 ' 工具性 ' 使用来匹配资源和目标，以及 ' 拟态吸收 '，即从人类学习启发式，以随机和普遍的方式表现出来。我们提供了证据，表明尽管 AI 缺乏固有目标或自我意识，但它表现出与资源合理人类认知原则一致的精确性和效率的自适应平衡，这与有界理性和双过程理论的经典理论阐述一致。