Hierarchical Generative Agents for Simulating Sequential Human Behavior

Maria G. Mendoza, Lucas Waldburger, Jin Lee, S. Shankar Sastry

Keywords: LLM agents, multi-agent systems, behaviorally realistic agents, cognitively grounded AI, disaster evacuation modeling

TL;DR: We introduce a cognitively grounded simulation framework that uses persona-conditioned LLM agents to model realistic, sequential human evacuation behavior in dynamic disaster environments.

Abstract: Complex cognitive, emotional, and social processes shape human evacuations during natural disasters. Accurate modeling and understanding of human behavior in disasters or emergencies can greatly impact the evacuation process by informing more effective planning and resource allocation. However, collecting human data in these situations is very difficult, and existing computational evacuation models assume rational, homogeneous behavior, leading to unrealistic, overly optimistic predictions. To address this gap, we present a simulation framework of sequential human decision-making during an evacuation scenario, introducing cognitively grounded, persona-driven agents. Our framework models evacuation behavior in a grid-based urban environment that evolves over time, capturing fire and other hazards. Human agents are modeled as personas that make sequential decisions in response to environmental stimuli with cognition structured in three levels: high-level evacuation goals, mid-level route reasoning, and low-level navigation. Decision-making is driven by large language models (LLMs) coupled with a cognitive module and calibrated with empirical human evacuation data. We propose a dynamic, stimulus-driven disaster simulation framework that models human evacuation decision-making using persona-conditioned LLM agents and a cognitive hierarchy.

Submission Number: 78