qvib.pro
RU

From RAG to agentic retrieval

What for: understand the shift from "one query, one answer" to an agent that plans, rewrites queries and searches repeatedly.

профи

Survey on Agentic RAG, arXiv 2501.09136 (январь 2025) — оформление подхода как отдельного направления checked 2026-06-01

Updated: 02.07.2026

From RAG to agentic retrieval

What it is

Agentic RAG is the evolution of classic Retrieval-Augmented Generation. Instead of "one retrieval pass → stuff it into the prompt → answer", the agent plans steps, rewrites queries, calls tools, consults memory and iteratively refines the result while judging its own output. Retrieval becomes multi-step and self-correcting.

Where it came from

  • 2023–24 — classic RAG became the standard way to "hook an LLM up to your own data".
  • January 2025 — the survey paper "Agentic RAG: A Survey" (arXiv 2501.09136) comes out and frames the approach as a field of its own.
  • 2025 — vendors (Redis, RAGFlow, agent frameworks) move the logic from "pipelines" to "agents".

Why it took off

  • Static RAG handles complex multi-step questions poorly — you need adaptivity.
  • Self-evaluation and repeated retrieval reduce hallucinations: in several measurements errors drop from 20%+ to under 10%.
  • It coincided with the industry's general turn towards agents: "search" naturally became one of an agent's abilities.

How to use it today

  1. If you already have RAG — add a step where the agent reformulates the query when the results are weak.
  2. Give the agent several sources and tools, and the right to choose where to go for the answer.
  3. Build in verification: the agent grades its own answer and searches again when unsure.

What to watch out for

  • Multi-step is more expensive and slower than single-pass RAG — it isn't justified everywhere.
  • More steps means more places to fail; you need caps on iterations.
  • Quality still bottoms out at the quality of your sources: garbage in, garbage out.

Читать по-русски →