A Survey on LLM-powered Agents for Recommender Systems

2025-02-14

AI Summary

Traditional recommender systems face significant limitations in modeling complex user preferences and delivering interpretable recommendations. This paper presents a systematic review of large language model (LLM)-based agents in recommendation, introducing— for the first time—the recommendation-oriented, interaction-oriented, and simulation-oriented paradigms. We unify their core architectural components (user profiling, memory, planning, and execution) and propose a standardized evaluation framework. Our key contribution is the first taxonomy of LLM-agent recommenders grounded in these three paradigms, identifying critical research frontiers: enhanced interpretability, dynamic multi-turn interaction modeling, and multi-agent collaborative simulation. Leveraging natural-language interfaces, domain-specific benchmark datasets, and standardized evaluation protocols, we clarify the technical landscape, address existing gaps, and construct a structured knowledge graph. This work establishes both theoretical foundations and practical pathways toward next-generation recommender systems that are interpretable, adaptive, and embodied.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Large language models for search

Abstract

Recommender systems are essential components of many online platforms, yet traditional approaches still struggle with understanding complex user preferences and providing explainable recommendations. The emergence of Large Language Model (LLM)-powered agents offers a promising approach by enabling natural language interactions and interpretable reasoning, potentially transforming research in recommender systems. This survey provides a systematic review of the emerging applications of LLM-powered agents in recommender systems. We identify and analyze three key paradigms in current research: (1) Recommender-oriented approaches, which leverage intelligent agents to enhance the fundamental recommendation mechanisms; (2) Interaction-oriented approaches, which facilitate dynamic user engagement through natural dialogue and interpretable suggestions; and (3) Simulation-oriented approaches, which employ multi-agent frameworks to model complex user-item interactions and system dynamics. Beyond paradigm categorization, we analyze the architectural foundations of LLM-powered recommendation agents, examining their essential components: profile construction, memory management, strategic planning, and action execution. Our investigation extends to a comprehensive analysis of benchmark datasets and evaluation frameworks in this domain. This systematic examination not only illuminates the current state of LLM-powered agent recommender systems but also charts critical challenges and promising research directions in this transformative field.

Problem

• Enhance complex user preference understanding
• Provide explainable recommendations via LLM
• Explore LLM-powered agent paradigms in recommender systems

Innovation

• LLM-powered natural language interactions
• Interpretable reasoning for recommendations
• Multi-agent simulation frameworks