MAS4POI: a Multi-Agents Collaboration System for Next POI Recommendation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913511589806080 |
|---|---|
| author | Wu, Yuqian Peng, Yuhong Yu, Jiapeng Lee, Raymond S. T. |
| author_facet | Wu, Yuqian Peng, Yuhong Yu, Jiapeng Lee, Raymond S. T. |
| contents | LLM-based Multi-Agent Systems have potential benefits of complex decision-making tasks management across various domains but their applications in the next Point-of-Interest (POI) recommendation remain underexplored. This paper proposes a novel MAS4POI system designed to enhance next POI recommendations through multi-agent interactions. MAS4POI supports Large Language Models (LLMs) specializing in distinct agents such as DataAgent, Manager, Analyst, and Navigator with each contributes to a collaborative process of generating the next POI recommendations.The system is examined by integrating six distinct LLMs and evaluated by two real-world datasets for recommendation accuracy improvement in real-world scenarios. Our code is available at https://github.com/yuqian2003/MAS4POI. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13700 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MAS4POI: a Multi-Agents Collaboration System for Next POI Recommendation Wu, Yuqian Peng, Yuhong Yu, Jiapeng Lee, Raymond S. T. Information Retrieval Artificial Intelligence Social and Information Networks LLM-based Multi-Agent Systems have potential benefits of complex decision-making tasks management across various domains but their applications in the next Point-of-Interest (POI) recommendation remain underexplored. This paper proposes a novel MAS4POI system designed to enhance next POI recommendations through multi-agent interactions. MAS4POI supports Large Language Models (LLMs) specializing in distinct agents such as DataAgent, Manager, Analyst, and Navigator with each contributes to a collaborative process of generating the next POI recommendations.The system is examined by integrating six distinct LLMs and evaluated by two real-world datasets for recommendation accuracy improvement in real-world scenarios. Our code is available at https://github.com/yuqian2003/MAS4POI. |
| title | MAS4POI: a Multi-Agents Collaboration System for Next POI Recommendation |
| topic | Information Retrieval Artificial Intelligence Social and Information Networks |
| url | https://arxiv.org/abs/2409.13700 |