Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918514204344320 |
|---|---|
| author | Gong, Yaxin Gao, Chongming Fan, Chenxiao Liu, Haoyan Wang, Wenjie Sun, Jianshan Li, Yangyang Feng, Fuli He, Xiangnan |
| author_facet | Gong, Yaxin Gao, Chongming Fan, Chenxiao Liu, Haoyan Wang, Wenjie Sun, Jianshan Li, Yangyang Feng, Fuli He, Xiangnan |
| contents | Recent advances in large language models (LLMs) have stimulated growing interest in agent-based recommender systems, enabling language-driven interaction and reasoning for more expressive preference modeling. However, most existing agentic approaches remain predominantly user-centric, treating items as passive entities and neglecting the interests of other critical stakeholders. This limitation exacerbates exposure concentration and long-tail under-representation, threatening long-term system sustainability. In this work, we identify this fundamental limitation and propose the first Tri-party LLM-agent Recommendation framework (TriRec) that explicitly coordinates user utility, item exposure, and platform-level fairness. The framework employs a two-stage architecture: Stage 1 empowers item agents with personalized self-promotion to improve matching quality and alleviate cold-start barriers, while Stage 2 performs platform-level sequential multi-objective re-ranking, balancing user relevance, item utility, and exposure fairness. Experiments show consistent gains in accuracy, fairness, and item-level utility. Moreover, we find that item self-promotion can simultaneously enhance fairness and effectiveness, challenging the conventional trade-off assumption between relevance and fairness. Our code is available at https://github.com/Marfekey/TriRec. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_10673 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation Gong, Yaxin Gao, Chongming Fan, Chenxiao Liu, Haoyan Wang, Wenjie Sun, Jianshan Li, Yangyang Feng, Fuli He, Xiangnan Information Retrieval Recent advances in large language models (LLMs) have stimulated growing interest in agent-based recommender systems, enabling language-driven interaction and reasoning for more expressive preference modeling. However, most existing agentic approaches remain predominantly user-centric, treating items as passive entities and neglecting the interests of other critical stakeholders. This limitation exacerbates exposure concentration and long-tail under-representation, threatening long-term system sustainability. In this work, we identify this fundamental limitation and propose the first Tri-party LLM-agent Recommendation framework (TriRec) that explicitly coordinates user utility, item exposure, and platform-level fairness. The framework employs a two-stage architecture: Stage 1 empowers item agents with personalized self-promotion to improve matching quality and alleviate cold-start barriers, while Stage 2 performs platform-level sequential multi-objective re-ranking, balancing user relevance, item utility, and exposure fairness. Experiments show consistent gains in accuracy, fairness, and item-level utility. Moreover, we find that item self-promotion can simultaneously enhance fairness and effectiveness, challenging the conventional trade-off assumption between relevance and fairness. Our code is available at https://github.com/Marfekey/TriRec. |
| title | Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2603.10673 |