Multi-Agent Video Recommenders: Evolution, Patterns, and Open Challenges

TL;DR

This survey explores the evolution, patterns, and challenges of multi-agent video recommender systems, highlighting recent advances with large language models and outlining future research directions.

Contribution

It provides a comprehensive taxonomy of multi-agent video recommenders, analyzes coordination mechanisms, and discusses emerging LLM-powered architectures and open challenges.

Findings

Multi-agent architectures improve recommendation explainability.

LLM integration enables more dynamic and personalized recommendations.

Open challenges include scalability and multimodal understanding.

Abstract

Video recommender systems are among the most popular and impactful applications of AI, shaping content consumption and influencing culture for billions of users. Traditional single-model recommenders, which optimize static engagement metrics, are increasingly limited in addressing the dynamic requirements of modern platforms. In response, multi-agent architectures are redefining how video recommender systems serve, learn, and adapt to both users and datasets. These agent-based systems coordinate specialized agents responsible for video understanding, reasoning, memory, and feedback, to provide precise, explainable recommendations. In this survey, we trace the evolution of multi-agent video recommendation systems (MAVRS). We combine ideas from multi-agent recommender systems, foundation models, and conversational AI, culminating in the emerging field of large language model (LLM)-powered MAVRS. We present a taxonomy of collaborative patterns and analyze coordination mechanisms across diverse video domains, ranging from short-form clips to educational platforms. We discuss representative frameworks, including early multi-agent reinforcement learning (MARL) systems such as MMRF and recent LLM-driven architectures like MACRec and Agent4Rec, to illustrate these patterns. We also outline open challenges in scalability, multimodal understanding, incentive alignment, and identify research directions such as hybrid reinforcement learning-LLM systems, lifelong personalization and self-improving recommender systems.