AMAP Agentic Planning Technical Report
By: Yulan Hu, Xiangwen Zhang, Sheng Ouyang, Hao Yi, Lu Xu, Qinglin Lang, Lide Tan, Xiang Cheng, Tianchen Ye, Zhicong Li, Ge Chen, Wenjin Yang, Zheng Pan, Shaopan Xiong, Siran Yang, Ju Huang, Yan Zhang, Jiamang Wang, Yong Liu, Yinfeng Huang, Tucheng Lin, Xin Li, Ning Guo
Published: 2025-12-31
View on arXiv →Abstract
This technical report introduces STAgent, an agentic large language model developed by Alibaba Amap, specifically engineered for real-world spatio-temporal reasoning and complex planning. It achieves superior performance in practical tasks such as multi-modal route planning and Point of Interest (POI) discovery. The model demonstrates efficiency and often outperforms larger general-purpose models within its specialized domain while robustly maintaining strong general reasoning and tool-use capabilities.