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

arXiv: https://arxiv.org/abs/2603.10673 · HTML: https://mlsanity.com/paper/2603.10673/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 17 of 17)

- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [Reinforced Latent Reasoning for LLM-based Recommendation](https://mlsanity.com/paper/2505.19092/) (2025)
- [Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation](https://mlsanity.com/paper/2307.04571/) (2023)
- [SimUSER: Simulating User Behavior with Large Language Models for Recommender System Evaluation](https://mlsanity.com/paper/2504.12722/) (2025)
- [TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providers](https://mlsanity.com/paper/2104.09024/) (2021)
- [NextQuill: Causal Preference Modeling for Enhancing LLM Personalization](https://mlsanity.com/paper/2506.02368/) (2025)
- [LLM-Enhanced User-Item Interactions: Leveraging Edge Information for Optimized Recommendations](https://mlsanity.com/paper/2402.09617/) (2024)
- [iAgent: LLM Agent as a Shield between User and Recommender Systems](https://mlsanity.com/paper/2502.14662/) (2025)
- [Dynamic fairness-aware recommendation through multi-agent social choice](https://mlsanity.com/paper/2303.00968/) (2023)
- [STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning](https://mlsanity.com/paper/2508.18812/) (2025)
- [A Personalized Framework for Consumer and Producer Group Fairness Optimization in Recommender Systems](https://mlsanity.com/paper/2402.00485/) (2024)
- [HLLM-Creator: Hierarchical LLM-based Personalized Creative Generation](https://mlsanity.com/paper/2508.18118/) (2025)
- [Don't Start Over: A Cost-Effective Framework for Migrating Personalized Prompts Between LLMs](https://mlsanity.com/paper/2601.12034/) (2026)
- [LTP-MMF: Towards Long-term Provider Max-min Fairness Under Recommendation Feedback Loops](https://mlsanity.com/paper/2308.05902/) (2023)

## Built on by (most cited first, 2 of 2)

- [The User Asks, Platforms Compete: How Agentic Recommendation Markets Take Shape](https://mlsanity.com/paper/2607.25253/) (2026)
- [Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce It](https://mlsanity.com/paper/2610.03195/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have spurred interest in agent-based recommender systems, yet most agentic approaches remain user-centric: items stay passive entities whose exposure is a by-product of relevance ranking, which exacerbates exposure concentration and long-tail under-representation. We break this user-centric allocation of agency with a Tri-party LLM-agent Recommendation framework (TriRec). Responsibility is split deliberately: Stage 1 has each item generate self-promotion conditioned on the target user, which lowers cold-start barriers, while the exposure budget stays with the platform, whose Stage 2 sequential re-ranker balances relevance, item utility, and exposure fairness. On four public datasets TriRec improves accuracy, fairness, and item-level utility, with the accuracy gain significant on three of the four. A three-arm ablation at 50 candidates separates two levels of the mechanism on items that received no exposure during training: self-promotion drives the accuracy gain, and conditioning it on the target user adds further exposure, together raising these items' share of top-ranked exposure by 43.6% relative. Restricting promotions to catalogue-verifiable attributes cuts strong exaggeration to 0.5%/2.0% on two datasets while retaining 88.6%/92.0% of the accuracy gain. Our code is available at https://github.com/Marfekey/TriRec.