mlsanityData to 14 Oct 2026

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

arXiv 2506.21805 ↗First posted 26 Jun 2025cs.AI cs.CLcited by 28

On the map: LLM agents and tool use → Multimodal and embodied agents

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.

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.

Builds on

11 of 27 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation18 Apr

Other references · 10

  1. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  2. 2023Can Large Language Models Be an Alternative to Human Evaluations?cited by 734
  3. 2023Large Language Models Empowered Agent-based Modeling and Simulation: A Survey and Perspectivescited by 257
  4. 2024LLM Agents Grounded in Self-Reports Enable General-Purpose Simulation of Individualscited by 249
  5. 2023Agents: An Open-source Framework for Autonomous Language Agentscited by 116
  6. 2023Humanoid Agents: Platform for Simulating Human-like Generative Agentscited by 73
  7. 2025SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluationcited by 33
  8. 2024Large Language Models as Recommender Systems: A Study of Popularity Biascited by 26
  9. 2024Generative Adversarial Reviews: When LLMs Become the Criticcited by 12
  10. 2025Towards an LLM-powered Social Digital Twinning Platformcited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 23.

28 papers.

Sort:

By area:

  1. 2025Emergent Social Dynamics of LLM Agents in the El Farol Bar Problemcited by 8
  2. 2026AlignUSER: Human-Aligned LLM Agents via World Models for Recommender System Evaluationcited by 6
  3. 2025CP-Env: Evaluating Large Language Models on Clinical Pathways in a Controllable Hospital Environmentcited by 4
  4. 2026Social Simulacra in the Wild: AI Agent Communities on Moltbookcited by 4
  5. 2026Beyond Offline A/B Testing: Context-Aware Agent Simulation for Recommender System Evaluationcited by 3
  6. 2025Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agentscited by 2
  7. 2026When Plausible Is Not Realistic: Evaluating Human Mobility in LLM-Based Urban Simulationcited by 2
  8. 2025Integrating LLM and Diffusion-Based Agents for Social Simulationcited by 1
  9. 2025Privacy-Preserving Synthetic Dataset of Individual Daily Trajectories for City-Scale Mobility Analyticscited by 1
  10. 2026Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generationcited by 1
  11. 2026LiveCultureBench: a Multi-Agent, Multi-Cultural Benchmark for Large Language Models in Dynamic Social Simulationscited by 1
  12. 2026OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligencecited by 1
16 more
  1. 2026Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modelingcited by 1
  2. 2026PerceptUI: LLM Agents as Human-Aligned Synthetic Users for UI/UX Evaluationcited by 1
  3. 2026CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platformcited by 1
  4. 2026Step-Level Preference Learning for Generative Agents in Social Simulationscited by 1
  5. 2026Evaluating Few-Shot Temporal Reasoning of LLMs for Human Activity Prediction in Smart Environmentscited by 0
  6. 2026Mobility-Aware Cache Framework for Scalable LLM-Based Human Mobility Simulationcited by 0
  7. 2026Evidence-based Distributional Alignment for Large Language Modelscited by 0
  8. 2026Cross-Cultural Simulation of Citizen Emotional Responses to Bureaucratic Red Tape Using LLM Agentscited by 0
  9. 2026TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Controlcited by 0
  10. 2026AGORA: Can Deliberation and Governance Gates Absorb Participation Bias in Transit Planning?cited by 0
  11. 2026Agent-driven Long-tail Simulation for Autonomous Drivingcited by 0
  12. 2026Empirical Grounding Improves the Realism of LLM Agents Simulating Human Behavior During Disruptionscited by 0
  13. 2026CityReal: Human-Aligned Urban Behavior and City Dynamics Simulation with Large-Scale LLM Agentscited by 0
  14. 2026Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environmentscited by 0
  15. 2026Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety Judgmentscited by 0
  16. 2026Measuring the Behavioral Fidelity of Long-Horizon Human Activity Simulationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents
  2. 2024GenSim: A General Social Simulation Platform with Large Language Model based Agents
  3. 2026GenWorld: Empirically Grounded Urban Simulation Infrastructure for Scalable LLM-Agent Studies
  4. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society
  5. 2025Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications
  6. 2025TrajLLM: A Modular LLM-Enhanced Agent-Based Framework for Realistic Human Trajectory Simulation
  7. 2025AI Urban Scientist: Multi-Agent Collaborative Automation for Urban Research
  8. 2025Exploring Large Language Model Agents for Piloting Social Experiments