Research

Paper

AI LLM March 11, 2026

Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation

Authors

Yaxin Gong, Chongming Gao, Chenxiao Fan, Wenjie Wang, Fuli Feng, Xiangnan He

Abstract

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 uses a platform agent for sequential multi-objective re-ranking, balancing user relevance, item utility, and exposure fairness. Experiments on multiple benchmarks 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.

Metadata

arXiv ID: 2603.10673
Provider: ARXIV
Primary Category: cs.IR
Published: 2026-03-11
Fetched: 2026-03-12 04:21

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.10673v1</id>\n    <title>Breaking User-Centric Agency: A Tri-Party Framework for Agent-Based Recommendation</title>\n    <updated>2026-03-11T11:40:13Z</updated>\n    <link href='https://arxiv.org/abs/2603.10673v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.10673v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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 uses a platform agent for sequential multi-objective re-ranking, balancing user relevance, item utility, and exposure fairness. Experiments on multiple benchmarks 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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n    <published>2026-03-11T11:40:13Z</published>\n    <arxiv:primary_category term='cs.IR'/>\n    <author>\n      <name>Yaxin Gong</name>\n    </author>\n    <author>\n      <name>Chongming Gao</name>\n    </author>\n    <author>\n      <name>Chenxiao Fan</name>\n    </author>\n    <author>\n      <name>Wenjie Wang</name>\n    </author>\n    <author>\n      <name>Fuli Feng</name>\n    </author>\n    <author>\n      <name>Xiangnan He</name>\n    </author>\n  </entry>"
}