aiqbench analysis
This study demonstrates a spatially grounded agent-based framework that leverages LLMs to simulate individual decision-making during infectious disease outbreaks, integrating real-world census data to capture social and geographic heterogeneity. The analysis identifies income and education as primary drivers of reporting behavior, while geography and model choice exert smaller, consistent influences on simulation outcomes. By generating synthetic data that reflects demographic diversity, this approach offers a robust tool for bias-aware behavioral analysis and spatial epidemiological modeling.
An Infectious Disease Spread Simulation Based on Large Language Model Decision Making
arXiv:2606.06360v2 Announce Type: replace Abstract: Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective public health interventions. Prior work has shown that large language models can simulate realistic human behaviour by generating agent decisions based on demographic prompts and situational context. We build on this foundation with a spatially grounded, agent-based simulation framework that integrates LLM-generated decisions about self-reported influenza-like illness into a census-based synthetic population of agents. Location is treated as a central feature: agents are assigned to spatial units within cities, capturing the spatial distributions of different demographic groups using real-world census data and enabling geographically diverse behavioural modelling. We implement and compare three decision scenarios, independent reasoning, household influence, and message framing, and simulate self-reporting outcomes in San Francisco and Atlanta. Results reveal that income and education are the dominant drivers of reporting rate variation, with smaller but consistent effects from geography, LLM model choice, and message framing. Our framework generates synthetic data that captures both social and geographic heterogeneity, supporting spatial epidemiological modelling and bias-aware behavioural analysis.
Abstract:Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective public health interventions. Prior work has shown that large language models can simulate realistic human behaviour by generating agent decisions based on demographic prompts and situational context. We build on this foundation with a spatially grounded, agent-based simulation framework that integrates LLM-generated decisions about self-reported influenza-like illness into a census-based synthetic population of agents. Location is treated as a central feature: agents are assigned to spatial units within cities, capturing the spatial distributions of different demographic groups using real-world census data and enabling geographically diverse behavioural modelling. We implement and compare three decision scenarios, independent reasoning, household influence, and message framing, and simulate self-reporting outcomes in San Francisco and Atlanta. Results reveal that income and education are the dominant drivers of reporting rate variation, with smaller but consistent effects from geography, LLM model choice, and message framing. Our framework generates synthetic data that captures both social and geographic heterogeneity, supporting spatial epidemiological modelling and bias-aware behavioural analysis.
Artificial Intelligence (cs.AI)
arXiv:2606.06360 [cs.AI]
(or arXiv:2606.06360v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2606.06360 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 265 words
Related coverage
An Infectious Disease Spread Simulation Based on Large Language Model Decision Making
arXiv · Jun 6, 2026
How might continual learning affect safety and alignment?
LessWrong · Jun 13, 2026
I Did This Without Your Knowledge
LessWrong · Oct 17, 2026
Would We See It Coming? Preference Falsification Cascades in Multi-Agent Systems
LessWrong · Aug 4, 2026