Tag
This paper evaluates zero-shot large language models for predicting neighborhood-level mobility patterns across U.S. metropolitan areas, comparing them to supervised baselines and auditing their structural alignment with empirical data.
The paper proposes FairGIN, a fairness-aware graph neural network for demand prediction in expanding bike-sharing systems, addressing cold-start expansion and spatial inequities to promote equitable low-carbon mobility.
UrbanAgent is a tool-augmented agent framework that uses LLMs with code execution, API calls, and MCP to handle cross-system urban requests. The authors also introduce UrbanEval, a benchmark for evaluating task results and execution quality, achieving 71% success rate over baselines.
This paper introduces UrbanDS, a graph-guided LLM multi-agent system designed for data-intensive urban tasks, along with UrbanDS-Bench, a benchmark for evaluating such systems. Experiments show it outperforms existing data science agents and has been deployed in a real-world urban operations platform.
This paper proposes UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem using multi-agent collaborative reasoning and tool-augmented evidence retrieval. It outperforms baselines on global urban datasets for carbon emissions, GDP, and population estimation, achieving an average 8.1% improvement in R².
The author uses a photo of scuff marks on a subway station wall to estimate the height distribution of commuters, applying image processing and a heuristic body-to-scuff ratio, and discusses potential improvements using Bayesian methods.
Introduces CausalPOI, a spatio-temporal graph-based causal representation learning framework for cold-start POI check-in forecasting, which outperforms state-of-the-art baselines on real-world SafeGraph datasets.