Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG

TL;DR

This survey explores Agentic Retrieval-Augmented Generation, highlighting its ability to enhance LLMs with autonomous agents for dynamic, multi-step reasoning and real-time data integration across various applications.

Contribution

It provides a taxonomy, comparative analysis, and practical insights into Agentic RAG architectures, applications, and open challenges, advancing understanding of this emerging paradigm.

Findings

Agentic RAG enables dynamic retrieval and multi-agent collaboration.

The survey classifies architectures based on agent control and autonomy.

Applications span healthcare, finance, education, and enterprise domains.

Abstract

Large Language Models (LLMs) have advanced artificial intelligence by enabling human-like text generation and natural language understanding. However, their reliance on static training data limits their ability to respond to dynamic, real-time queries, resulting in outdated or inaccurate outputs. Retrieval-Augmented Generation (RAG) has emerged as a solution, enhancing LLMs by integrating real-time data retrieval to provide contextually relevant and up-to-date responses. Despite its promise, traditional RAG systems are constrained by static workflows and lack the adaptability required for multi-step reasoning and complex task management. Agentic Retrieval-Augmented Generation (Agentic RAG) transcends these limitations by embedding autonomous AI agents into the RAG pipeline. These agents leverage agentic design patterns reflection, planning, tool use, and multi-agent collaboration to dynamically manage retrieval strategies, iteratively refine contextual understanding, and adapt workflows through operational structures ranging from sequential steps to adaptive collaboration. This integration enables Agentic RAG systems to deliver flexibility, scalability, and context-awareness across diverse applications. This paper presents an analytical survey of Agentic RAG systems. It traces the evolution of RAG paradigms, introduces a principled taxonomy of Agentic RAG architectures based on agent cardinality, control structure, autonomy, and knowledge representation, and provides a comparative analysis of design trade-offs across existing frameworks. The survey examines applications in healthcare, finance, education, and enterprise document processing, and distills practical lessons for system designers and practitioners. Finally, it identifies key open research challenges related to evaluation, coordination, memory management, efficiency, and governance, outlining directions for future research.