Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
By Aditi Singh, Abul Ehtesham, Saket Kumar, T. T. Khoei. arXiv.org, 2025
354 citations recorded by the source corpus.
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their reliance on static training data limits their ability to respond to dynamic, real-time queries, resulting in outdated or inaccurate outputs.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.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/ba7952e7c4fb891c36980ca19f94251257da6eb7
Citations in the corpus
- AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges (2025, neutral): “This structured coordination allows for more complex goal pur-11”
- LLM Web Dynamics: Tracing Model Collapse in a Network of LLMs (2025, unknown): “…showing equal or better performance in particular tasks comparing to fine-tuning in empirical studies (Balaguer et al., 2024; Cheng et al., 2025; Singh et al., 2025; Gupta et al., 2024), making it a practical and low-cost surrogate for iterative learning and training within the framework of…”
- Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval (2026, unknown): “Beyond that, there is active exploration into leveraging these models within more sophisticated frameworks like Retrieval-Augmented Generation (RAG) pipelines (Gao et al., 2023; Cheng et al., 2025; Gan et al., 2025a) and Agentic systems (Singh et al., 2025) to tackle complex document-based settings.”