How Personal Characteristics Shape User Exploration of Diverse Movie Recommendations with a LLM-Based Multi-Agent System

TL;DR

This study examines how a Large Language Model-based multi-agent recommender system enhances user exploration of diverse movie recommendations and how personal traits influence user experience.

Contribution

It demonstrates that multi-agent systems increase perceived novelty and diversity, and highlights the role of personality and skepticism in user interactions.

Findings

Multi-agent system significantly boosts perceived novelty and diversity.

Conscientiousness correlates with higher perceived accuracy and diversity.

Extraversion correlates with lower perceived diversity.

Abstract

Diversity is an important evaluation criterion for recommender systems beyond accuracy, yet users differ in their willingness to engage with novel and diverse content. In this work, we investigate how a Large Language Model (LLM)-based multi-agent system supports users' exploration of diverse recommendations, and how individual characteristics shape user experiences. We conducted a between-subjects user study (N = 100) comparing a single-agent system (baseline) with a multi-agent system for movie recommendations. We measured Perceived Accuracy, diversity, novelty, and overall rating, and examined the influence of personal characteristics, including personality traits, demographics, GenAI recommendation experience, and GenAI skepticism. Results show that the multi-agent system significantly increases Perceived Novelty and Shannon Diversity. Conscientiousness is positively associated with Perceived Accuracy and diversity, whereas extraversion is negatively associated with Perceived Diversity. Prior experience with GenAI-based recommendations is positively associated with Shannon Diversity, while skepticism toward GenAI is negatively associated with it. We also observe significant interaction effects between system design and user characteristics. These findings highlight the importance of personality-aware conversational recommender systems and caution against one-size-fits-all multi-agent designs.