Agentic RAG: making retrieval a decision the agent controls

Short answer

Agentic RAG is retrieval-augmented generation where the agent decides when to retrieve, what to query, and whether the results are good enough — sometimes searching again — instead of running a fixed retrieve-then-generate pipeline. Retrieval stops being a pre-step bolted onto the prompt and becomes a tool the orchestrator can call, evaluate, and re-call until the context is sufficient to answer.

This page goes deep on the retrieval layer specifically. For how retrieval sits among the other five components of an agent system, see agentic AI architecture; this page is the part it points to.

The short version

Classic RAG is a straight line: take the user's question, embed it, search a vector index, stuff the top chunks into the prompt, generate. It runs once, the same way, every time. That is enough for a lot of question-answering, and you should not reach past it without a reason.

Agentic RAG: making retrieval a decision the agent controls

Related reading

Agentic RAG: What Happens When Retrieval Becomes a Decision Instead of a Step

9 RAG Techniques That Actually Improve Retrieval Quality

Agentic RAG: Designing Self-Correcting Retrieval Loops for Production

Retrieval-Augmented Generation (RAG) Explained 2026

rag-explained-how-it-works

End-to-End RAG Workflow: How Retrieval Augmented Generation Works