# Agentic RAG

> 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.

- Identifier: PTL-0134
- Category: Retrieval & Tool Use
- Canonical URL: https://protologue.com/t/agentic-rag/
- Also known as: agent-based RAG, iterative retrieval
- Introduced: 2025

## 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.

## Broader terms

- [Retrieval-Augmented Generation](https://protologue.com/t/retrieval-augmented-generation/)

## Related terms

- [AI Agent](https://protologue.com/t/ai-agent/)
- [ReAct](https://protologue.com/t/react/)
- [Query Rewriting](https://protologue.com/t/query-rewriting/)
- [Self-RAG](https://protologue.com/t/self-rag/)
- [Corrective RAG](https://protologue.com/t/corrective-rag/)

## Sources

- Singh et al. (2025). Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG. https://arxiv.org/abs/2501.09136

## Cite this entry

Protologue. (2026). Agentic RAG. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0134). https://protologue.com/t/agentic-rag/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)