Distilling Aggregate Mobility Statistics into a Language Model Policy for Post-Event Crowd Simulation

An Agent-Based Crowd Simulation Framework Integrating Urban Walkway Networks and Individual Pedestrian Behaviors for Congestion Analysis

: High-density crowd accidents in complex urban walkway networks represent significant public safety risks characterized by non-linear dynamics and unpredictable emergence. While existing crowd models have primarily focused on evacuation within controlled facilities, they often lack the capacity to explain how behavioral heterogeneity interacts with real-world walkway networks to generate localized congestion. This paper proposes an Agent-Based Modeling (ABM) framework specifically designed to analyze the impact of diverse pedestrian behavior compositions on network-wide congestion dynamics. The proposed framework adopts a centralized time-stepped execution structure that integrates complex movement factors, including multi-destination trip chains and density-responsive navigation. To demonstrate its practical utility, the framework is applied to a realistic urban scenario in the Itaewon district, Seoul, utilizing empirical datasets on transportation demand and network topology. The study investigates how varying the distribution of behavior profiles—such as shortest-path, route-choice, and crowd-avoid strategies—reshapes emergent crowding patterns. The results highlight the framework’s strength as a robust scenario-based analysis tool for identifying systemic risks and providing actionable insights for crowd management in dense urban environments.

From Urban Mobility to Epidemic Dynamics: A Mixture-of-Experts Framework with Preference Alignment for Policy Scenario Simulation

Non-pharmaceutical interventions (NPIs) alter epidemic risk through behavioral reallocations, not simply aggregate mobility reductions. Scenario-based NPI analysis therefore requires a behavioral layer that translates alternative policy calendars into plausible activity and mobility trajectories before downstream outcomes are simulated. We introduce UrbanShare-MoE-PA, a data-driven agent-level framework that maps factual and alternative NPI calendars to daily time-allocation trajectories and propagates them through a calibrated behavior-driven SEIR simulator. The behavioral engine decomposes each agent-day into travel share, POI-category allocation conditional on staying, and travel-mode allocation conditional on traveling. It combines a structured UrbanShare baseline, mixture-of-experts heads for heterogeneous POI and mode responses, and phase-aware preference alignment for calendar-conditioned rollouts. Using data from 911 agents in Singapore observed from March to August 2020, we evaluate factual reconstruction, four alternative lockdown calendars, and epidemic-activity trade-offs. UrbanShare-MoE improves POI reconstruction over the baseline, while UrbanShare-MoE-PA achieves the lowest travel-mode errors and the clearest alternative-calendar trajectories. In the calibrated SEIR simulation, early lockdown lowers infectious burden, late lockdown increases it, and short lockdown preserves the highest weighted activity with only a modest increase in epidemic burden relative to the original policy. These results show that epidemic-activity conclusions depend on how policy calendars are translated into behavior, and that agent-level mobility-share modeling provides an interpretable bridge between policy timing, behavior, and downstream simulation.

Designing A Scalable LLM Agent Framework for Large-scale Urban Segregation Simulation

Agent-based models (ABMs) have long been employed to explore how individual behaviors aggregate into complex societal phenomena in urban space. The rise of Large Language Models (LLMs) offers a new paradigm for ABM, enabling high-fidelity modeling of human behavior. However, urban dynamics often require extensive agent interactions to emerge, and scaling up LLM agent simulations is limited by high-latency remote LLM inference and high costs. To address this, we propose the OpenCity framework for large-scale LLM agent simulation. We design a novel "Group-and-Distill" strategy that significantly reduces costs without sacrificing behavioral diversity by aggregating agents with shared static characteristics while preserving their unique dynamic states. Moreover, a system-level request scheduler is designed to optimize I/O concurrency and communication bottlenecks. Experiments in six cities globally demonstrate that OpenCity achieves a 600x speedup and a 45% reduction in token usage compared to standard baseline models, while maintaining 96% behavioral consistency with independently invoked agent baselines. Based on OpenCity, we conduct first benchmark test on large-scale social segregation with LLM agents. The results show that OpenCity-accelerated generative agents are effective in reproducing socioeconomic segregation patterns. Furthermore, our scalability analysis demonstrates that the realism of emerging social phenomena increases as the agents scale up, quantitatively validating the necessity of large-scale simulations. Finally, we demonstrate the framework's capability as a policy sandbox through a counterfactual analysis of urban equity. Overall, OpenCity provides a robust and efficient framework that unlocks the potential of LLMs for large-scale, high-fidelity multi-agent systems analysis. Code repo is available at https://github.com/tsinghua-fib-lab/OpenCity.

An Agentic Approach for Active Data Collection, Travel Behavior Modeling, and Weather-Sensitive Demand Prediction

Overall, the study shows how conversational surveys, structured data processing, conventional behavioral modeling, machine learning, and multimodal LLM prediction can be coordinated within an auditable multi-agent workflow.

Mobility, Memory, and Network Structure in Agent-Based Models of Convention Tipping and Convergence

A unified predictive model is introduced that accurately estimates how structural and behavioral parameters determine the time required for complete adoption, showing that mobility is the dominant accelerator while memory and connectivity modulate convergence in systematic ways.

UrbanMix: LLM-Guided Simulation of Mixed Autonomy Traffic with Heterogeneous Behavioral Profiles