This work proposes UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem, and extends indicator prediction as a closed-loop process of active evidence acquisition and iterative reasoning, enabling agents to verify uncertain inferences through tool-augmented retrie...
Xixuan Hao, Yutian Jiang, Jiabo Liu et al.· Proceedings of the 32nd ACM...· 2 citations
Geospatial representation learning from satellite imagery is a fundamental problem for large-scale urban analysis and real-world applications. Despite recent advances, current methods struggle with cross-region generalization and semantic interpretability due to their reliance on region-specific auxiliary data and the...
Yutian Jiang, Jiabo Liu, Xixuan Hao et al.· 1 citation
This work reformulate geo-localization as a human-like perceive-then-verify reasoning problem and proposes GeoPAVE (Geo-localization Perception-and-Verification-Engine), a bi-level agentic framework that contains perception-based hypothesis generation via single-pass rollouts and verification-based evidence grounding f...
Yutian Jiang, Rui-Ji Li, Sisuo Lyu et al.· 0 citations
A Two TimeScale Reinforcement Learning framework (TSRL), which separates decision-making into two cooperative layers and significantly outperforms baselines, achieving average system profit improvements of 20.1% in Hangzhou and 46.6% in Shanghai.
