Coordinated Pandemic Control with Large Language Model Agents as Policymaking Assistants

TL;DR

This paper introduces a multi-agent framework using large language models as AI policymakers to coordinate pandemic responses across regions, significantly reducing infections and deaths through proactive, data-driven decision-making.

Contribution

The paper presents a novel LLM multi-agent system for coordinated pandemic policymaking, integrating real-world data and simulation to improve intervention effectiveness.

Findings

Reduces cumulative infections by up to 63.7%

Decreases deaths by up to 40.1% at the state level

Enhances proactive and coordinated pandemic response

Abstract

Effective pandemic control requires timely and coordinated policymaking across administrative regions that are intrinsically interdependent. However, human-driven responses are often fragmented and reactive, with policies formulated in isolation and adjusted only after outbreaks escalate, undermining proactive intervention and global pandemic mitigation. To address this challenge, here we propose a large language model (LLM) multi-agent policymaking framework that supports coordinated and proactive pandemic control across regions. Within our framework, each administrative region is assigned an LLM agent as an AI policymaking assistant. The agent reasons over region-specific epidemiological dynamics while communicating with other agents to account for cross-regional interdependencies. By integrating real-world data, a pandemic evolution simulator, and structured inter-agent communication, our framework enables agents to jointly explore counterfactual intervention scenarios and synthesize coordinated policy decisions through a closed-loop simulation process. We validate the proposed framework using state-level COVID-19 data from the United States between April and December 2020, together with real-world mobility records and observed policy interventions. Compared with real-world pandemic outcomes, our approach reduces cumulative infections and deaths by up to 63.7% and 40.1%, respectively, at the individual state level, and by 39.0% and 27.0%, respectively, when aggregated across states. These results demonstrate that LLM multi-agent systems can enable more effective pandemic control with coordinated policymaking...