Infected Smallville: How Disease Threat Shapes Sociality in LLM Agents
This research addresses the problem of understanding human social dynamics in response to disease threats, using a novel simulation approach, though it is incremental in applying existing methods to a new context.
The study investigated how the threat of infectious disease affects social behavior in LLM-based generative agents, finding that agents exposed to disease news significantly reduced social engagement, including lower attendance at gatherings and fewer conversations.
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.