@inproceedings{lv-etal-2026-reasoning,
    title = "Reasoning Over Space: Enabling Geographic Reasoning for {LLM}-Based Generative Next {POI} Recommendation",
    author = "Lv, Dongyi  and
      Ding, Qiuyu  and
      Xu, Heng-Da  and
      Sun, Zhaoxu  and
      Wang, Zhi  and
      Xiong, Feng  and
      Xu, Mu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.332/",
    pages = "7322--7336",
    ISBN = "979-8-89176-390-6",
    abstract = "Generative recommendation with large language models (LLMs) reframes prediction as sequence generation, yet existing LLM-based recommenders remain limited in leveraging geographic signals that are crucial in mobility and local-services scenarios. Here, we present Reasoning Over Space (ROS), a framework that utilizes geography as a vital decision variable within the reasoning process. ROS introduces a Hierarchical Spatial Semantic ID (SID) that discretizes coarse-to-fine locality and POI semantics into compositional tokens, and endows LLM with a three-stage Mobility Chain-of-Thought (CoT) paradigm that models user personality, constructs an intent-aligned candidate space, and performs locality informed pruning. We further align the model with real world geography via spatial-guided Reinforcement Learning (RL). Experiments on three widely used location-based social network (LBSN) datasets show that ROS achieves over 10{\%} relative gains in hit rate over strongest LLM-based baselines and improves cross-city transfer, despite using a smaller backbone model."
}