Tag
A developer used Apple Maps data to create a video game where players can explore and interact with the entire city of San Francisco, including climbing buildings and stealing cars.
Japanese researchers developed CitySim, an urban simulator powered by LLMs that populates a digital twin of Tokyo with up to 1 million autonomous AI agents, accurately predicting real-world patterns like commuting and shopping behavior.
CityBehavEx is a scalable LLM-assisted urban simulation platform that combines established human mobility models with fine-tuned cross-encoders to generate realistic, empirically validated mobility patterns for city-sized populations, demonstrating 100,000 agents over 75 days in under one hour on a single consumer GPU.
This paper introduces a validation framework to evaluate whether LLM-based urban simulators reproduce empirical human mobility patterns. Using data from Paris and Shanghai, the authors find a substantial gap between plausible narratives and realistic mobility constraints, and provide open infrastructure for reproducible evaluation.