Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation

• URL: http://arxiv.org/abs/2605.11807v1
• Date: Tue, 12 May 2026 09:01:29 GMT
• Title: Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation
• Abstract summary: Agent-based World knowledge Augmented REcommendation (AWARE)<n>AWARE generates contextual narratives that capture regional cultural characteristics, seasonal trends, and ongoing events relevant to each user.<n>AWARE consistently outperforms competitive baselines, achieving up to 12.4% relative improvement.
• Score: 6.2314068624703465
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generative point-of-interest (POI) recommendation models based on large language models (LLMs) have shown promising results by formulating next POI prediction as a sequence generation task. However, the knowledge encoded in these models remains fixed after training, making them unable to perceive evolving real-world conditions that shape user mobility decisions, such as local events and cultural trends. To bridge this gap, we propose AWARE (Agent-based World knowledge Augmented REcommendation), which employs an LLM agent to generate location- and time-aware contextual narratives that capture regional cultural characteristics, seasonal trends, and ongoing events relevant to each user. Rather than introducing generic or noisy information, AWARE further anchors these narratives in each user's behavioral context, grounding external world knowledge in personalized spatial-temporal patterns. Extensive experiments on three real-world datasets demonstrate that AWARE consistently outperforms competitive baselines, achieving up to 12.4% relative improvement.

Related papers

• Think2Go: Generative Next POI Recommendation with LLM Reasoning [57.37706163990998]
  Next Point-of-Interest (POI) recommendation task focuses on mining user behavioral preference patterns from historical check-ins to provide personalized suggestions for the next destination.<n>Existing methods rely on shallow contextual information and handcrafted feature interactions to predict the next POI.<n>We propose Think2Go, a novel generative next POI recommendation framework, which enhances the model's comprehension of SID representations and explores diverse spatial-temporal patterns via test-time computational scaling.
  arXiv  Detail & Related papers  (2026-07-31T03:52:20Z)
• Self-Evolving World Models for LLM Agent Planning [72.99782619992361]
  We introduce WorldEvolver, a self-evolving world model framework that revises its deployment-time context while keeping the downstream agent and all model parameters frozen.<n>WorldEvolver achieves the highest prediction accuracy across three backbones and leads other world model baselines on downstream agent success rate.
  arXiv  Detail & Related papers  (2026-06-29T17:58:43Z)
• Online Experiential Learning for Language Models [99.90826536842337]
  Online Experiential Learning (OEL) is a framework that enables language models to continuously improve from their own deployment experience.<n>OEL operates in two stages: first, transferable experiential knowledge is extracted and accumulated from interaction trajectories collected on the user side.<n>We evaluate OEL on text-based game environments across multiple model scales and both thinking and non-thinking variants.
  arXiv  Detail & Related papers  (2026-03-17T17:57:49Z)
• Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams [78.9560820155271]
  We evaluate online adaptation over streaming, continually updating knowledge.<n> OAKS comprises two datasets: OAKS-BABI and OAKS-Novel.<n>Both state-of-the-art models and agentic memory systems fail to adapt robustly on OAKS.
  arXiv  Detail & Related papers  (2026-03-08T00:38:39Z)
• FedUTR: Federated Recommendation with Augmented Universal Textual Representation for Sparse Interaction Scenarios [58.33672784127872]
  Federated recommendations (FRs) have emerged as an on-device privacy-preserving paradigm.<n>We propose a novel method named FedUTR, which incorporates item textual representations as a complement to interaction behaviors.<n>Our method achieves superior performance, with improvements of up to 59% across all datasets compared to the SOTA baselines.
  arXiv  Detail & Related papers  (2026-01-29T08:55:19Z)
• Predicting the Future by Retrieving the Past [23.181638022094038]
  We propose Predicting the Future by Retrieving the Past (PFRP), a novel approach that explicitly integrates global historical data to enhance forecasting accuracy.<n>PFRP produces more accurate and interpretable forecasts by adaptively combining global predictions with the outputs of any local prediction model.
  arXiv  Detail & Related papers  (2025-11-08T05:24:45Z)
• Cognitive-Aligned Spatio-Temporal Large Language Models For Next Point-of-Interest Prediction [22.412601522965144]
  Large language models (LLMs) have shown great potential in recommender systems, which treat the next POI prediction in a generative manner.<n>In industrial-scale POI prediction applications, incorporating world knowledge and alignment of human cognition, such as seasons, weather conditions, holidays, and users' profiles, can enhance the user experience.<n>We propose CoAST, a framework employing natural language as an interface, next for the incorporation of world knowledge, unstructured-temporal trajectory patterns, profiles, and situational information.
  arXiv  Detail & Related papers  (2025-10-16T14:05:28Z)
• GSTM-HMU: Generative Spatio-Temporal Modeling for Human Mobility Understanding [12.79351579779076]
  We introduce GSTM-HMU, a generative temporal-temporal framework to advance mobility analysis.<n>We conduct experiments on four widely used real-world datasets, including Gowalla, WeePlace, Brightkite, and FourSquare.
  arXiv  Detail & Related papers  (2025-09-23T15:20:38Z)
• LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation [45.02469804709771]
  We propose LaDi-WM, a world model that predicts the latent space of future states using diffusion modeling.<n>We show that LaDi-WM significantly enhances policy performance by 27.9% on the LIBERO-LONG benchmark and 20% on the real-world scenario.
  arXiv  Detail & Related papers  (2025-05-13T04:42:14Z)
• World-Consistent Data Generation for Vision-and-Language Navigation [33.13590164890286]
  Vision-and-Language Navigation (VLN) is a challenging task that requires an agent to navigate through photorealistic environments following natural-language instructions.<n>One main obstacle existing in VLN is data scarcity, leading to poor generalization performance over unseen environments.<n>We propose the world-consistent data generation (WCGEN), an efficacious data-augmentation framework satisfying both diversity and world-consistency.
  arXiv  Detail & Related papers  (2024-12-09T11:40:54Z)
• ALP: Action-Aware Embodied Learning for Perception [60.64801970249279]
  We introduce Action-Aware Embodied Learning for Perception (ALP) ALP incorporates action information into representation learning through a combination of optimizing a reinforcement learning policy and an inverse dynamics prediction objective. We show that ALP outperforms existing baselines in several downstream perception tasks.
  arXiv  Detail & Related papers  (2023-06-16T21:51:04Z)
• Self-supervised Graph-based Point-of-interest Recommendation [66.58064122520747]
  Next Point-of-Interest (POI) recommendation has become a prominent component in location-based e-commerce. We propose a Self-supervised Graph-enhanced POI Recommender (S2GRec) for next POI recommendation. In particular, we devise a novel Graph-enhanced Self-attentive layer to incorporate the collaborative signals from both global transition graph and local trajectory graphs.
  arXiv  Detail & Related papers  (2022-10-22T17:29:34Z)
• Modelling of Bi-directional Spatio-Temporal Dependence and Users' Dynamic Preferences for Missing POI Check-in Identification [38.51964956686177]
  We develop a model, named Bi-STDDP, which can integrate bi-directional-temporal dependence and users' dynamic preferences. Results demonstrate significant improvements of our model compared with state-of-the-art methods.
  arXiv  Detail & Related papers  (2021-12-31T03:54:37Z)

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.