Boxuan Wang — Page 2

arXiv2025

Estimates of the reproduction ratio from epidemic surveillance may be biased in spatially structured populations

Accurate estimates of the reproduction ratio are crucial to project infectious disease epidemic evolution and guide public health response. Here, we prove that estimates of the reproduction ratio based on inference from surveillance data can be inaccurate if the population comprises spatially distinct communities, as the space-mobility interplay may hide the true epidemic evolution from surveillance data. Consequently, surveillance may underestimate the reproduction ratio over long periods, even mistaking growing epidemics as subsiding. To address this, we use the spectral properties of the matrix describing the spatial epidemic spread to reweigh surveillance data. We propose a correction that removes the bias across all epidemic phases. We validate this correction against simulated epidemics and use COVID-19 as a case study. However, our results apply to any epidemic where mobility is a driver of circulation. Our findings will help improve epidemic monitoring and surveillance and inform strategies for public health response.

physics.soc-ph↗

arXiv2024

Can LLMs Understand Social Norms in Autonomous Driving Games?

Social norm is defined as a shared standard of acceptable behavior in a society. The emergence of social norms fosters coordination among agents without any hard-coded rules, which is crucial for the large-scale deployment of AVs in an intelligent transportation system. This paper explores the application of LLMs in understanding and modeling social norms in autonomous driving games. We introduce LLMs into autonomous driving games as intelligent agents who make decisions according to text prompts. These agents are referred to as LLM-based agents. Our framework involves LLM-based agents playing Markov games in a multi-agent system (MAS), allowing us to investigate the emergence of social norms among individual agents. We aim to identify social norms by designing prompts and utilizing LLMs on textual information related to the environment setup and the observations of LLM-based agents. Using the OpenAI Chat API powered by GPT-4.0, we conduct experiments to simulate interactions and evaluate the performance of LLM-based agents in two driving scenarios: unsignalized intersection and highway platoon. The results show that LLM-based agents can handle dynamically changing environments in Markov games, and social norms evolve among LLM-based agents in both scenarios. In the intersection game, LLM-based agents tend to adopt a conservative driving policy when facing a potential car crash. The advantage of LLM-based agents in games lies in their strong operability and analyzability, which facilitate experimental design.

cs.AI↗