ModelRefs / Agentic RAG — AI Glossary
Agentic RAG — AI Glossary
A RAG pattern where an agent decides whether, when, and what to retrieve, using tools to query knowledge sources iteratively. Also called agent-driven RAG.
Overview
Agentic RAG replaces the static retrieve-then-generate pipeline with an LLM agent equipped with retrieval tools. The agent can issue multiple queries, evaluate retrieved content quality, retrieve follow-up information, and decide when it has sufficient context to answer. Implemented via function-calling or ReAct patterns.
Reference details
| Topic | rag |
|---|---|
| Also known as | agent-driven RAG |
| Last reviewed | 2026-06-24 |
Related terms
Commonly confused with
The retrieval decision moves into the model: whether to retrieve at all, what to search for, and whether to search again. That is the difference from a fixed pipeline, which always retrieves exactly once. It overlaps with Self-RAG and Corrective RAG, which are specific published mechanisms for parts of the same idea, whereas this names the general pattern.
Continue your research
Use these connected ModelRefs sections to compare alternatives, inspect implementation paths, and review the evidence and governance boundaries relevant to Agentic RAG — AI Glossary.
Frequently asked questions
What is Agentic RAG?
A RAG pattern where an agent decides whether, when, and what to retrieve, using tools to query knowledge sources iteratively.
Is Agentic RAG the same as agent-driven RAG?
Yes — agent-driven RAG are common aliases for Agentic RAG.
What concepts are related to Agentic RAG?
Closely related concepts include modular rag, self rag, agent.