# CitySim: Modeling Urban Behaviors and City Dynamics with Large-Scale LLM-Driven Agent Simulation

arXiv: https://arxiv.org/abs/2506.21805 · HTML: https://mlsanity.com/paper/2506.21805/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 26 Jun 2025.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 11 of 11)

- [CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society](https://mlsanity.com/paper/2303.17760/) (2023)
- [Can Large Language Models Be an Alternative to Human Evaluations?](https://mlsanity.com/paper/2305.01937/) (2023)
- [Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectives](https://mlsanity.com/paper/2312.11970/) (2023)
- [LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individuals](https://mlsanity.com/paper/2411.10109/) (2024)
- [Agents: An Open-source Framework for Autonomous Language Agents](https://mlsanity.com/paper/2309.07870/) (2023)
- [Humanoid Agents: Platform for Simulating Human-like Generative Agents](https://mlsanity.com/paper/2310.05418/) (2023)
- [SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation](https://mlsanity.com/paper/2504.12722/) (2025)
- [Large Language Models as Recommender Systems: A Study of Popularity Bias](https://mlsanity.com/paper/2406.01285/) (2024)
- [Generative Adversarial Reviews: When LLMs Become the Critic](https://mlsanity.com/paper/2412.10415/) (2024)
- [MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation](https://mlsanity.com/paper/2504.16946/) (2025)
- [Towards an LLM-powered Social Digital Twinning Platform](https://mlsanity.com/paper/2505.10681/) (2025)

## Built on by (most cited first, 28 of 28)

- [Emergent Social Dynamics of LLM Agents in the El Farol Bar Problem](https://mlsanity.com/paper/2509.04537/) (2025)
- [AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System Evaluation](https://mlsanity.com/paper/2601.00930/) (2026)
- [CP-Env: Evaluating Large Language Models on Clinical Pathways in a Controllable Hospital Environment](https://mlsanity.com/paper/2512.10206/) (2025)
- [Social Simulacra in the Wild: AI Agent Communities on Moltbook](https://mlsanity.com/paper/2603.16128/) (2026)
- [Beyond Offline A/B Testing: Context-Aware Agent Simulation for Recommender System Evaluation](https://mlsanity.com/paper/2604.09549/) (2026)
- [Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents](https://mlsanity.com/paper/2510.17491/) (2025)
- [When Plausible Is Not Realistic: Evaluating Human Mobility in LLM-Based Urban Simulation](https://mlsanity.com/paper/2606.13835/) (2026)
- [Integrating LLM and Diffusion-Based Agents for Social Simulation](https://mlsanity.com/paper/2510.16366/) (2025)
- [Privacy-Preserving Synthetic Dataset of Individual Daily Trajectories for City-Scale Mobility Analytics](https://mlsanity.com/paper/2512.17239/) (2025)
- [Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generation](https://mlsanity.com/paper/2602.07083/) (2026)
- [LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulations](https://mlsanity.com/paper/2603.01952/) (2026)
- [OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence](https://mlsanity.com/paper/2603.14771/) (2026)
- [Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling](https://mlsanity.com/paper/2605.19418/) (2026)
- [PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluation](https://mlsanity.com/paper/2606.05697/) (2026)
- [CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platform](https://mlsanity.com/paper/2607.12086/) (2026)
- [Step-Level Preference Learning for Generative Agents in Social Simulations](https://mlsanity.com/paper/2607.14485/) (2026)
- [Evaluating Few-Shot Temporal Reasoning of LLMs for Human Activity Prediction in Smart Environments](https://mlsanity.com/paper/2602.11176/) (2026)
- [Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulation](https://mlsanity.com/paper/2602.16727/) (2026)
- [Evidence-based Distributional Alignment for Large Language Models](https://mlsanity.com/paper/2603.13305/) (2026)
- [Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agents](https://mlsanity.com/paper/2604.12545/) (2026)
- [TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control](https://mlsanity.com/paper/2604.17456/) (2026)
- [AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning?](https://mlsanity.com/paper/2606.13696/) (2026)
- [Agent-driven Long-tail Simulation for Autonomous Driving](https://mlsanity.com/paper/2607.04331/) (2026)
- [Empirical Grounding Improves the Realism of LLM Agents Simulating Human Behavior During Disruptions](https://mlsanity.com/paper/2607.17437/) (2026)
- [CityReal: Human-Aligned Urban Behavior and City Dynamics Simulation with Large-Scale LLM Agents](https://mlsanity.com/paper/2608.16897/) (2026)
- [Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments](https://mlsanity.com/paper/2608.22833/) (2026)
- [Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety Judgments](https://mlsanity.com/paper/2608.26188/) (2026)
- [Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulations](https://mlsanity.com/paper/2609.01257/) (2026)

## Abstract (arXiv)

Modeling human behavior in urban environments is fundamental for social science, behavioral studies, and urban planning. Prior work often rely on rigid, hand-crafted rules, limiting their ability to simulate nuanced intentions, plans, and adaptive behaviors. Addressing these challenges, we envision an urban simulator (CitySim), capitalizing on breakthroughs in human-level intelligence exhibited by large language models. In CitySim, agents generate realistic daily schedules using a recursive value-driven approach that balances mandatory activities, personal habits, and situational factors. To enable long-term, lifelike simulations, we endow agents with beliefs, long-term goals, and spatial memory for navigation. CitySim exhibits closer alignment with real humans than prior work, both at micro and macro levels. Additionally, we conduct insightful experiments by modeling tens of thousands of agents and evaluating their collective behaviors under various real-world scenarios, including estimating crowd density, predicting place popularity, and assessing well-being. Our results highlight CitySim as a scalable, flexible testbed for understanding and forecasting urban phenomena.