Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation

• URL: http://arxiv.org/abs/2601.04562v1
• Date: Thu, 08 Jan 2026 03:46:03 GMT
• Title: Reasoning Over Space: Enabling Geographic Reasoning for LLM-Based Generative Next POI Recommendation
• Authors: Dongyi Lv, Qiuyu Ding, Heng-Da Xu, Zhaoxu Sun, Zhi Wang, Feng Xiong, Mu Xu,
• Abstract summary: Reasoning Over Space (ROS) is a framework that utilizes geography as a vital decision variable within the reasoning process.<n> ROS introduces a Hierarchical Spatial Semantic ID (SID) that discretizes coarse-to-fine locality and POI semantics into compositional tokens.<n>We further align the model with real world geography via spatial-guided Reinforcement Learning (RL)
• Score: 8.829656404389178
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Unleashing MLLMs on the Edge: A Unified Framework for Cross-Modal ReID via Adaptive SVD Distillation [48.88299242238335]
  Cross-Modal Re-identification (CM-ReID) faces challenges due to maintaining a fragmented ecosystem of specialized cloud models.<n>We propose MLLMEmbed-ReID, a unified framework based on a powerful cloud-edge architecture.
  arXiv  Detail & Related papers  (2026-02-13T13:48:08Z)
• RSGround-R1: Rethinking Remote Sensing Visual Grounding through Spatial Reasoning [61.84363374647606]
  Remote Sensing Visual Grounding (RSVG) aims to localize target objects in large-scale aerial imagery based on natural language descriptions.<n>These descriptions often rely heavily on positional cues, posing unique challenges for Multimodal Large Language Models (MLLMs) in spatial reasoning.<n>We propose a reasoning-guided, position-aware post-training framework, dubbed textbfRSGround-R1, to progressively enhance spatial understanding.
  arXiv  Detail & Related papers  (2026-01-29T12:35:57Z)
• Wireless Traffic Prediction with Large Language Model [54.07581399989292]
  TIDES is a novel framework that captures spatial-temporal correlations for wireless traffic prediction.<n> TIDES achieves efficient adaptation to domain-specific patterns without incurring excessive training overhead.<n>Our results indicate that integrating spatial awareness into LLM-based predictors is the key to unlocking scalable and intelligent network management in future 6G systems.
  arXiv  Detail & Related papers  (2025-12-19T04:47:40Z)
• SpatialGeo:Boosting Spatial Reasoning in Multimodal LLMs via Geometry-Semantics Fusion [23.86761713752287]
  Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks.<n>Most MLLMs suffer from limited spatial reasoning ability to interpret and infer spatial arrangements in three-dimensional space.<n>We propose a novel vision encoder based on hierarchical fusion of geometry and semantics features, generating spatial-aware visual embedding.
  arXiv  Detail & Related papers  (2025-11-21T15:24:33Z)
• LLM-Aligned Geographic Item Tokenization for Local-Life Recommendation [21.430438767288106]
  LGSID is an LLM-Hierarchical Geographic Item Tokenization Framework for Local-life Recommendation.<n>We introduce a novel G-DPO algorithm that uses pre-trained reward model to inject generalized spatial knowledge and collaborative signals into LLMs.<n>Experiments on real-world Kuaishou industry datasets show that LGSID consistently outperforms state-of-the-art discriminative and generative recommendation models.
  arXiv  Detail & Related papers  (2025-11-18T07:54:32Z)
• Spatial Preference Rewarding for MLLMs Spatial Understanding [92.25703021388142]
  Multimodal large language models (MLLMs) have demonstrated promising spatial understanding capabilities.<n>Despite their successes, MLLMs still fall short in fine-grained spatial perception abilities.<n>We propose a Spatial Preference Rewarding(SPR) approach that enhances MLLMs' spatial capabilities.
  arXiv  Detail & Related papers  (2025-10-16T07:16:18Z)
• RALLM-POI: Retrieval-Augmented LLM for Zero-shot Next POI Recommendation with Geographical Reranking [7.085868567930685]
  Next point-of-interest (POI) recommendation predicts a user's next destination from historical movements.<n>Traditional models require intensive training, while LLMs offer flexible and generalizable zero-shot solutions.<n>We propose RALLM-POI, a framework that couples LLMs with retrieval-augmented generation and self-rectification.
  arXiv  Detail & Related papers  (2025-09-21T12:52:28Z)
• Can LLMs Learn to Map the World from Local Descriptions? [50.490593949836146]
  This study investigates whether Large Language Models (LLMs) can construct coherent global spatial cognition.<n> Experiments conducted in a simulated urban environment demonstrate that LLMs exhibit latent representations aligned with real-world spatial distributions.
  arXiv  Detail & Related papers  (2025-05-27T08:22:58Z)
• Geography-Aware Large Language Models for Next POI Recommendation [21.03555605703108]
  Next Point-of-Interest (POI) recommendation task aims to predict users' next destinations based on their historical movement data.<n>We propose GA-LLM (Geography-Aware Large Language Model), a novel framework that enhances Large Language Models with two specialized components.<n>Experiments on three real-world datasets demonstrate the state-of-the-art performance of GA-LLM.
  arXiv  Detail & Related papers  (2025-05-18T03:20:20Z)
• SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models [70.01883340129204]
  spatial reasoning is a crucial component of both biological and artificial intelligence. We present a comprehensive study of the capability of current state-of-the-art large language models (LLMs) on spatial reasoning.
  arXiv  Detail & Related papers  (2024-06-07T01:06:34Z)
• GeoLLM: Extracting Geospatial Knowledge from Large Language Models [49.20315582673223]
  We present GeoLLM, a novel method that can effectively extract geospatial knowledge from large language models. We demonstrate the utility of our approach across multiple tasks of central interest to the international community, including the measurement of population density and economic livelihoods. Our experiments reveal that LLMs are remarkably sample-efficient, rich in geospatial information, and robust across the globe.
  arXiv  Detail & Related papers  (2023-10-10T00:03:23Z)
• LCPFormer: Towards Effective 3D Point Cloud Analysis via Local Context Propagation in Transformers [60.51925353387151]
  We propose a novel module named Local Context Propagation (LCP) to exploit the message passing between neighboring local regions. We use the overlap points of adjacent local regions as intermediaries, then re-weight the features of these shared points from different local regions before passing them to the next layers. The proposed method is applicable to different tasks and outperforms various transformer-based methods in benchmarks including 3D shape classification and dense prediction tasks.
  arXiv  Detail & Related papers  (2022-10-23T15:43:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.