🤖 AI Summary
Current information retrieval (IR) systems face challenges including shallow semantic understanding, limited reasoning capabilities, and low decision interpretability. Method: This work systematically reviews large language model (LLM)-powered agents for search and recommendation, proposing the first IR-oriented LLM agent taxonomy grounded in three dimensions: role definition, capability boundaries, and evolutionary paradigms. It integrates key techniques—including multi-agent coordination, tool-augmented execution, memory enhancement, reflective reasoning, and retrieval-augmented generation (RAG). Contribution/Results: We introduce the first unified, IR-specific classification framework for LLM agents; establish an open-source literature index repository on GitHub; and provide both theoretical foundations and practical guidelines for developing next-generation IR systems that are interpretable, adaptive, and task-driven.
📝 Abstract
Information technology has profoundly altered the way humans interact with information. The vast amount of content created, shared, and disseminated online has made it increasingly difficult to access relevant information. Over the past two decades, search and recommendation systems (collectively referred to as information retrieval systems) have evolved significantly to address these challenges. Recent advances in large language models (LLMs) have demonstrated capabilities that surpass human performance in various language-related tasks and exhibit general understanding, reasoning, and decision-making abilities. This paper explores the transformative potential of large language model agents in enhancing search and recommendation systems. We discuss the motivations and roles of LLM agents, and establish a classification framework to elaborate on the existing research. We highlight the immense potential of LLM agents in addressing current challenges in search and recommendation, providing insights into future research directions. This paper is the first to systematically review and classify the research on LLM agents in these domains, offering a novel perspective on leveraging this advanced AI technology for information retrieval. To help understand the existing works, we list the existing papers on agent-based simulation with large language models at this link: https://github.com/tsinghua-fib-lab/LLM-Agent-for-Recommendation-and-Search.