Back

Simulating population compliance with pandemic interventions using large language models

Liu, R.; Jong, C.; Li, H.; Cao, Y.; Yao, Q.; Yamana, T.; Pei, S.; Du, H.

2026-05-15 infectious diseases
10.64898/2026.05.12.26352942 medRxiv
Show abstract

Effective pandemic response requires accurate modeling of population compliance with non-pharmaceutical interventions (NPIs), yet most epidemic models treat behavioral change as fixed scenarios rather than an emergent process. Here, we test whether large language model (LLM)-based agents can generate individualized behavioral responses to time-varying NPIs and disease risk. We instantiate demographically representative agents in three U.S. cities (Boston, Denver, San Antonio) and condition them on evolving outbreak conditions and policies during the early COVID-19 pandemic, without fitting to observed mobility data. Across three frontier LLMs and their ensemble, agents generate zero-shot mobility changes across restaurants, retail, and entertainment venues, benchmarked against cellphone-derived foot-traffic records. The simulations recover average mobility trends across cities and venue types but exhibit overly narrow within-city variation. The three LLMs display distinct biases, while an ensemble approach improves robustness and overall performance. These findings establish LLM agents as a promising framework for modeling adherence to NPIs and highlight the need for further fine-tuning and empirical validation before they can support policy analysis.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

1
Nature Medicine
117 papers in training set
Top 0.1%
10.1%
2
Nature Communications
4913 papers in training set
Top 22%
8.4%
3
Epidemics
104 papers in training set
Top 0.1%
7.2%
4
PLOS Computational Biology
1633 papers in training set
Top 5%
6.8%
5
Scientific Reports
3102 papers in training set
Top 17%
6.4%
6
Journal of The Royal Society Interface
189 papers in training set
Top 0.5%
6.4%
7
Proceedings of the National Academy of Sciences
2130 papers in training set
Top 14%
4.9%
50% of probability mass above
8
Nature Computational Science
50 papers in training set
Top 0.1%
4.3%
9
npj Digital Medicine
97 papers in training set
Top 1%
4.0%
10
Science
429 papers in training set
Top 9%
3.6%
11
PLOS ONE
4510 papers in training set
Top 41%
3.3%
12
Physical Review X
23 papers in training set
Top 0.2%
1.9%
13
Cell Systems
167 papers in training set
Top 7%
1.8%
14
Bulletin of Mathematical Biology
84 papers in training set
Top 1%
1.7%
15
Medical Decision Making
10 papers in training set
Top 0.1%
1.7%
16
Communications Medicine
85 papers in training set
Top 0.3%
1.5%
17
eLife
5422 papers in training set
Top 47%
1.3%
18
Nature
575 papers in training set
Top 12%
1.3%
19
Science Advances
1098 papers in training set
Top 23%
1.2%
20
Emerging Infectious Diseases
103 papers in training set
Top 2%
1.2%
21
The Lancet Infectious Diseases
71 papers in training set
Top 2%
1.0%
22
iScience
1063 papers in training set
Top 24%
1.0%
23
PNAS Nexus
147 papers in training set
Top 1%
0.9%
24
Royal Society Open Science
193 papers in training set
Top 4%
0.9%
25
Nature Human Behaviour
85 papers in training set
Top 4%
0.8%
26
BMC Infectious Diseases
118 papers in training set
Top 5%
0.7%
27
Mathematical Biosciences
42 papers in training set
Top 1%
0.7%
28
PLOS Global Public Health
293 papers in training set
Top 6%
0.7%
29
BMC Medicine
163 papers in training set
Top 7%
0.7%
30
Annals of Internal Medicine
27 papers in training set
Top 1%
0.7%