In this paper, we propose a multi-agent collaboration framework called MATCHA for conversational recommendation system, leveraging large language models (LLMs) to enhance personalization and user engagement. Users can request recommendations via free-form text and receive curated lists aligned with their interests, preferences, and constraints. Our system introduces specialized agents for intent analysis, candidate generation, ranking, re-ranking, explainability, and safeguards. These agents collaboratively improve recommendations accuracy, diversity, and safety. On eight metrics, our model achieves superior or comparable performance to the current state-of-the-art. Through comparisons with six baseline models, our approach addresses key challenges in conversational recommendation systems for game recommendations, including: (1) handling complex, user-specific requests, (2) enhancing personalization through multi-agent collaboration, (3) empirical evaluation and deployment, and (4) ensuring safe and trustworthy interactions.
View on arXiv@article{hui2025_2504.20094,
title={ MATCHA: Can Multi-Agent Collaboration Build a Trustworthy Conversational Recommender? },
author={ Zheng Hui and Xiaokai Wei and Yexi Jiang and Kevin Gao and Chen Wang and Frank Ong and Se-eun Yoon and Rachit Pareek and Michelle Gong },
journal={arXiv preprint arXiv:2504.20094},
year={ 2025 }
}