Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling

2026-07-15

AI Summary

This work addresses the limited generalizability of existing urban profiling methods, which often rely on correlation-based assumptions and static pipelines, particularly in heterogeneous or unseen regions. The authors propose UrbanAgent, a novel framework that reframes urban profiling as an inference-driven reasoning task. UrbanAgent employs dedicated agents for each type of multi-source heterogeneous data and establishes a structured multi-agent collaboration mechanism to explicitly handle cross-modal inconsistencies. By integrating tool-augmented external knowledge retrieval with reinforcement learning, the framework enables active evidence acquisition and iterative reasoning. This approach uniquely transforms indicator prediction—such as carbon emissions, GDP, and population estimation—into a verifiable and iterative active reasoning process, achieving an average R² improvement of 8.1% over baseline methods and demonstrating strong generalization capabilities in previously unseen cities.

Abstract

Urban region profiling constitutes a core problem in urban computing, supporting applications such as population estimation, economic assessment, and environmental monitoring. Existing methods typically formulate this task as multimodal representation learning, fusing heterogeneous urban data, e.g., satellite imagery, points of interest, textual descriptions, and 3D building information, into latent embeddings for prediction. However, these approaches are largely correlation-driven, assume cross-modal consistency, and rely on static pipelines, which limit their robustness in heterogeneous or unseen urban regions. We propose UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem. UrbanAgent instantiates an independent agent for each data modality and performs structured multi-agent collaborative reasoning to explicitly address cross-modal inconsistencies rather than absorbing them into a single representation. In addition, UrbanAgent extends indicator prediction as a closed-loop process of active evidence acquisition and iterative reasoning, enabling agents to verify uncertain inferences through tool-augmented retrieval of external knowledge optimized via reinforcement learning. Extensive experiments on global urban datasets for Carbon emissions, GDP, and Population estimation show that UrbanAgent consistently outperforms existing baselines, achieving an average improvement of 8.1% in R2, and exhibiting strong generalization performance in unseen-city settings.

Problem

• urban region profiling
• multi-agent reasoning
• cross-modal inconsistency
• tool-augmented evidence
• heterogeneous urban data

Innovation

• multi-agent reasoning
• tool-augmented retrieval
• urban region profiling
• cross-modal inconsistency
• reinforcement learning