Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | https://arxiv.org/abs/2605.11807 |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911673601753088 |
|---|---|
| author | Ding, Qiuyu Xu, Heng-Da Zhang, Wei Lv, Dongyi Xia, Changda Xiong, Feng Xu, Mu |
| author_facet | Ding, Qiuyu Xu, Heng-Da Zhang, Wei Lv, Dongyi Xia, Changda Xiong, Feng Xu, Mu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_11807 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation Ding, Qiuyu Xu, Heng-Da Zhang, Wei Lv, Dongyi Xia, Changda Xiong, Feng Xu, Mu Artificial Intelligence 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. |
| title | Why Users Go There: World Knowledge-Augmented Generative Next POI Recommendation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2605.11807 |