Agentic RAG Survey: How the Research Splits the Field

Originally published at Agentic RAG Survey: How the Research Splits the Field on smartgate.network.

A shorter version of "Agentic RAG Survey: How the Research Splits the Field" — the full piece lives at smartgate.network.

What the full piece covers

• Memory, tools and reflection: the three axes the surveys split on — Two surveys do most of the organising. The 2023 retrieval survey (RAG for large language models) separated naive retrieval from advanced retrieval — pre-retrieval, retrieval and post-retrieval optimisation — and from modular retrieval, where the pipeline is a set of …
• Search as a tool for LLM-based agents: the interface the papers assume — Before reflection, routing or planning, there is one function that every method in the field calls.
• Self-reflection and the encoder underneath: OpenCode-style harnesses — The most-cited advance of 2023 and 2024 is self-critique.
• Initialization: when the harness starts and the clock begins — Evaluation is where the agentic RAG literature is least reproducible, and the reason is usually the clock.
• Pre-memory initialization: the state before the first write — There is a window in every run that the surveys never name: after the harness is running and before the first memory write exists.
• What the benchmarks measure, and what they leave out — The evaluation surveys are the honest part of the field.
• The gateway in the appendix: keys, revocation and reproducibility — Every published result was produced by calling a hosted endpoint, and almost none of them describe the operational layer that made it possible.
• What is agent memory, in the literature's own terms — The first question in any memory taxonomy is scope: which writes may a later read see.
• How SmartGate compares — The choice the survey creates is not which method to adopt; it is what your loop calls, and whether you can tell afterwards what each call was for.
• How to get started — Pick two methods, not five. Choose one iterative method and one reflective method from the survey, and note the four retrieval parameters each assumes.
• Limitations and what this does not do — Seven of the eight planned sections carry code.

Read the full piece: Agentic RAG Survey: How the Research Splits the Field on smartgate.network.