iAgent: LLM Agent as a Shield between User and Recommender Systems

TL;DR

This paper proposes a novel paradigm where an LLM-based agent acts as a protective intermediary between users and recommender systems, aiming to enhance user control and mitigate issues like manipulation and lack of personalization.

Contribution

Introduction of a user-agent-platform paradigm with an LLM agent serving as a shield to improve user protection and personalization in recommender systems.

Findings

The proposed paradigm enhances user control over recommendations.

LLM agents can effectively shield users from platform biases.

The approach addresses vulnerabilities in traditional recommender systems.

Abstract

Traditional recommender systems usually take the user-platform paradigm, where users are directly exposed under the control of the platform's recommendation algorithms. However, the defect of recommendation algorithms may put users in very vulnerable positions under this paradigm. First, many sophisticated models are often designed with commercial objectives in mind, focusing on the platform's benefits, which may hinder their ability to protect and capture users' true interests. Second, these models are typically optimized using data from all users, which may overlook individual user's preferences. Due to these shortcomings, users may experience several disadvantages under the traditional user-platform direct exposure paradigm, such as lack of control over the recommender system, potential manipulation by the platform, echo chamber effects, or lack of personalization for less active users due to the dominance of active users during collaborative learning. Therefore, there is an urgent need to develop a new paradigm to protect user interests and alleviate these issues. Recently, some researchers have introduced LLM agents to simulate user behaviors, these approaches primarily aim to optimize platform-side performance, leaving core issues in recommender systems unresolved. To address these limitations, we propose a new user-agent-platform paradigm, where agent serves as the protective shield between user and recommender system that enables indirect exposure.