LLM-powered reasoning in agent-based modeling

基于大语言模型推理的智能体建模

Abstract: Agent-based modeling (ABM) has the capability to model millions of individuals and their interactions, which is useful for policy making. However, ABMs have traditionally relied on static prior, which prevents the models from adapting to real-time changes. 摘要： 智能体建模（ABM）具备模拟数百万个体及其交互的能力，这对政策制定非常有用。然而，传统的 ABM 依赖于静态先验，这使得模型无法适应实时变化。

Our research provides a novel approach to addressing this information gap. Large language models (LLMs) offer new opportunities to predict human decision-making. 我们的研究提供了一种解决这一信息缺口的新方法。大语言模型（LLMs）为预测人类决策提供了新的机遇。

Here, we introduce a scalable Hybrid Agent-based and Language-driven Epidemic (HALE) modeling framework that leverages LLMs to predict human decision-making in an ABM simulation. As a proof-of-concept, we use HALE to simulate COVID-19 and its effects in Salt Lake County, UT. 在此，我们引入了一个可扩展的混合智能体与语言驱动流行病（HALE）建模框架，该框架利用大语言模型来预测 ABM 模拟中的人类决策。作为概念验证，我们使用 HALE 模拟了犹他州盐湖县的 COVID-19 疫情及其影响。

Paper Details: 论文详情：

Title: LLM-powered reasoning in agent-based modeling 标题： 基于大语言模型推理的智能体建模
Authors: Sifat Afroj Moon, Dakotah Maguire, Adam Spannaus, Joe Tuccillo, Maksudul Alam, Sudip K. Seal, John Gounley, Heidi Hanson 作者： Sifat Afroj Moon, Dakotah Maguire, Adam Spannaus, Joe Tuccillo, Maksudul Alam, Sudip K. Seal, John Gounley, Heidi Hanson
Subjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) 学科： 人工智能 (cs.AI)；多智能体系统 (cs.MA)
Submission Date: 7 Jul 2026 提交日期： 2026年7月7日