CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platform
Quick Answer
CityBehavEx is a scalable LLM-assisted urban simulation platform that integrates human mobility models with cross-encoders, enabling simulations of 100,000 agents in under an hour on a single GPU.
Quick Take
It supports empirical validation of generated mobility patterns against real-world data, enhancing the realism of urban simulations.
Key Points
- Simulates 100,000 agents over 75 days in under one hour on a consumer GPU.
- Combines human mobility models with fine-tuned cross-encoders for agent behavior.
- Allows users to define regions, launch experiments, and inspect trajectories.
- Validates generated routines against real-world mobility and semantic metrics.
- Enhances scalability and empirical validation in urban simulations.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Recent LLM-based multi-agent urban simulators can generate semantically rich city routines, but they remain costly to scale and are often weakly validated against empirical mobility patterns. We present CityBehavEx, an interactive LLM-assisted urban simulation platform that scales to city-size populations, exposes agent behavior for inspection, supports empirical validation, and generates mobility patterns that better match real-world spatial, temporal, and semantic distributions. Instead of invoking large language models for every agent action, CityBehavEx combines established human mobility models with fine-tuned cross-encoders that estimate semantic alignment between agent profiles, schedules, and activity transitions. This design enables large-scale simulations, as demonstrated in a case study of 100,000 agents over 75 days in under one hour on a single consumer GPU. The platform allows users to define simulation regions, launch experiments, inspect trajectories and activity traces, debug unrealistic behaviors, and validate generated routines against real-world mobility, time-use, and semantic metrics.
| Comments: | 10 pages, 3 figures |
| Subjects: | Computation and Language (cs.CL); Computers and Society (cs.CY); Multiagent Systems (cs.MA); Social and Information Networks (cs.SI) |
| Cite as: | arXiv:2607.12086 [cs.CL] |
| (or arXiv:2607.12086v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2607.12086 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Thiago H. Silva [view email]
[v1]
Mon, 13 Jul 2026 19:03:25 UTC (1,684 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CL
See more →TriAgent: Divergence-Aware Committees for Cost-Efficient Financial Sentiment Analysis
TriAgent introduces a cost-efficient multi-agent system for financial sentiment analysis, combining VADER, FinBERT, and Qwen2.5. It achieves an F1 score of ~0.87 with significant savings of $9.3M/year at a 10M-user scale compared to GPT-4o-mini, while also detecting hallucinations with an AUC of 0.90.