Infected Smallville: How Disease Threat Shapes Sociality in LLM Agents

TL;DR

This study uses large language model-based generative agent simulations to explore how infectious disease threats influence social behavior, revealing significant reductions in social engagement driven by disease-avoidance motivations.

Contribution

It demonstrates the use of generative agent-based modeling to experimentally investigate the impact of disease threat on sociality, a novel application of large language models in social simulation.

Findings

Agents reduced social interactions after reading about infectious diseases.

Agents explicitly linked behavioral changes to disease-avoidance motives.

Agents distinguished between infectious and noninfectious diseases, adjusting behavior accordingly.

Abstract

How does the threat of infectious disease influence sociality among generative agents? We used generative agent-based modeling (GABM), powered by large language models, to experimentally test hypotheses about the behavioral immune system. Across three simulation runs, generative agents who read news about an infectious disease outbreak showed significantly reduced social engagement compared to agents who received no such news, including lower attendance at a social gathering, fewer visits to third places (e.g., cafe, store, park), and fewer conversations throughout the town. In interview responses, agents explicitly attributed their behavioral changes to disease-avoidance motivations. A validity check further indicated that they could distinguish between infectious and noninfectious diseases, selectively reducing social engagement only when there was a risk of infection. Our findings highlight the potential of GABM as an experimental tool for exploring complex human social dynamics at scale.