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

TL;DR

This paper introduces TriRec, a novel tri-party framework for LLM-based recommendation systems that balances user preferences, item exposure, and fairness, improving accuracy and fairness simultaneously.

Contribution

It presents the first tri-party recommendation framework explicitly coordinating multiple stakeholders, with a two-stage architecture for personalized item promotion and platform-level re-ranking.

Findings

Experiments show improvements in accuracy, fairness, and item utility.

Item self-promotion enhances both fairness and effectiveness.

Challenging the traditional trade-off between relevance and fairness.

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 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.