{"ID":6621237,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12086","arxiv_id":"2607.12086","title":"CityBehavEx: A Scalable and Empirically Validated LLM-Assisted Urban Simulation Platform","abstract":"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.","short_abstract":"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 agen...","url_abs":"https://arxiv.org/abs/2607.12086","url_pdf":"https://arxiv.org/pdf/2607.12086v1","authors":"[\"Gustavo H. Santos\",\"Aline Viana\",\"Thiago H Silva\"]","published":"2026-07-13T19:03:25Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.CY\",\"cs.MA\",\"cs.SI\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}