The field of urban analytics and planning is witnessing a significant shift towards the integration of Large Language Models (LLMs) to enhance decision-making and simulation capabilities. Researchers are exploring the potential of LLMs in various applications, including historical cadastral data analysis, spatiotemporal reasoning, and urban mobility simulation. The use of LLMs is enabling the development of more accurate and efficient models for predicting urban phenomena, such as traffic patterns and population growth. Furthermore, LLMs are being used to support decision-making in urban planning, including the optimization of public transportation services and the analysis of remote sensing data. Notably, the incorporation of LLMs in urban analytics is allowing for the development of more interpretable and adaptable models, which can better capture the complexities of urban systems. Some noteworthy papers in this area include: LLM-Powered Agents for Navigating Venice's Historical Cadastre, which presents a novel approach to analyzing historical cadastral data using LLMs. USTBench: Benchmarking and Dissecting Spatiotemporal Reasoning of LLMs as Urban Agents, which introduces a benchmark for evaluating the spatiotemporal reasoning capabilities of LLMs in urban contexts. LLM-ODDR: A Large Language Model Framework for Joint Order Dispatching and Driver Repositioning, which proposes a framework for optimizing order dispatching and driver repositioning in ride-hailing services using LLMs.