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

2026-03-11

AI Summary

This work addresses the limitation of existing recommender systems that overly prioritize user preferences while neglecting item and platform interests, leading to concentrated exposure and insufficient coverage of long-tail items. To overcome this, the authors propose TriRec, a novel framework that introduces, for the first time, a tripartite agent collaboration mechanism powered by large language models. In the first stage, item agents perform personalized self-promotion to enhance match quality; in the second stage, a platform agent conducts multi-objective reranking to jointly optimize user relevance, item utility, and exposure fairness. Extensive experiments on multiple benchmark datasets demonstrate that TriRec significantly improves recommendation accuracy, item utility, and fairness, thereby challenging the conventional trade-off assumption between relevance and fairness and validating the efficacy and superiority of the tripartite collaborative paradigm.

Technology Category

• Multiagent Systems: Mechanism Design
• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• agent-based recommendation
• user-centric bias
• exposure fairness
• long-tail under-representation
• multi-stakeholder coordination

Innovation

• Tri-party recommendation
• LLM-based agents
• item self-promotion
• exposure fairness
• multi-objective re-ranking