Towards Efficient Hypergraph and Multi-LLM Agent Recommender Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912753210359808 |
|---|---|
| author | Mukande, Tendai Ali, Esraa Caputo, Annalina Dong, Ruihai OConnor, Noel |
| author_facet | Mukande, Tendai Ali, Esraa Caputo, Annalina Dong, Ruihai OConnor, Noel |
| contents | Recommender Systems (RSs) have become the cornerstone of various applications such as e-commerce and social media platforms. The evolution of RSs is paramount in the digital era, in which personalised user experience is tailored to the user's preferences. Large Language Models (LLMs) have sparked a new paradigm - generative retrieval and recommendation. Despite their potential, generative RS methods face issues such as hallucination, which degrades the recommendation performance, and high computational cost in practical scenarios. To address these issues, we introduce HGLMRec, a novel Multi-LLM agent-based RS that incorporates a hypergraph encoder designed to capture complex, multi-behaviour relationships between users and items. The HGLMRec model retrieves only the relevant tokens during inference, reducing computational overhead while enriching the retrieval context. Experimental results show performance improvement by HGLMRec against state-of-the-art baselines at lower computational cost. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06590 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Efficient Hypergraph and Multi-LLM Agent Recommender Systems Mukande, Tendai Ali, Esraa Caputo, Annalina Dong, Ruihai OConnor, Noel Information Retrieval Artificial Intelligence Multiagent Systems Recommender Systems (RSs) have become the cornerstone of various applications such as e-commerce and social media platforms. The evolution of RSs is paramount in the digital era, in which personalised user experience is tailored to the user's preferences. Large Language Models (LLMs) have sparked a new paradigm - generative retrieval and recommendation. Despite their potential, generative RS methods face issues such as hallucination, which degrades the recommendation performance, and high computational cost in practical scenarios. To address these issues, we introduce HGLMRec, a novel Multi-LLM agent-based RS that incorporates a hypergraph encoder designed to capture complex, multi-behaviour relationships between users and items. The HGLMRec model retrieves only the relevant tokens during inference, reducing computational overhead while enriching the retrieval context. Experimental results show performance improvement by HGLMRec against state-of-the-art baselines at lower computational cost. |
| title | Towards Efficient Hypergraph and Multi-LLM Agent Recommender Systems |
| topic | Information Retrieval Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2512.06590 |