{
  "id": "agentic-rag",
  "code": "PTL-0134",
  "term": "Agentic RAG",
  "aliases": [
    "agent-based RAG",
    "iterative retrieval"
  ],
  "category": "retrieval-tools",
  "definition": "Agentic RAG is retrieval-augmented generation in which an agent, rather than a fixed pipeline, decides whether to retrieve, what to search for, which sources or tools to use, and whether the evidence is sufficient, retrieving iteratively until it can answer.",
  "description": "A fixed pipeline retrieves once per question, so it fails on multi-hop questions and on queries that need reformulation. Agentic RAG handles them by planning, issuing follow-up searches, and reflecting on results, at the cost of more model calls, higher latency, and less predictable behavior. Self-RAG, corrective RAG, and active retrieval are earlier steps in the same direction.",
  "example": null,
  "broader": [
    "retrieval-augmented-generation"
  ],
  "narrower": [],
  "related": [
    "ai-agent",
    "react",
    "query-rewriting",
    "self-rag",
    "corrective-rag"
  ],
  "introduced": 2025,
  "added": "2026-10-10",
  "sources": [
    {
      "title": "Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG",
      "authors": "Singh et al.",
      "year": 2025,
      "url": "https://arxiv.org/abs/2501.09136"
    }
  ],
  "url": "https://protologue.com/t/agentic-rag/",
  "citation": "Protologue. (2026). Agentic RAG. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0134). https://protologue.com/t/agentic-rag/"
}