Will retrieval-augmented-generation (RAG) still be used in 2026?
➕
Plus
10
Ṁ671
2026
68%
chance

RAG is a type of information retrieval process. It modifies interactions with a large language model (LLM) so that it responds to queries with reference to a specified set of documents, using it in preference to information drawn from its own vast, static training data.

Will it still be used by cutting-edge technology companies in 2026 (EOY)?

Resolves NO if prominent players, e.g., Microsoft, Google, perplexity (or new entrants) publicly pivot away from RAG as mean of generating responses.
Resolve YES if this is still the state-of-the-art.

All forms of RAG count towards the resolution.

Agentic AIs that can look up sources on their own do not count.


Get
Ṁ1,000
and
S3.00
Sort by:
bought Ṁ50 YES

Agentic AIs are very vague. Technically, Perplexity Pro Search already rewrites your question into multiple search queries, so is that an Agentic AI?

Agreed that it is vague.
IMO, there is a qualitative difference between

1. A series of functions doing retrieval, dumping all into a context, and then running LLM for a generation.
2. An agent running on a cluster, that decides to browse the web or a DB and then outputs results using this information and its training.

The former is RAG, the latter is closer to AGI.
Perplexity pro is a complex series of functions, but still very much in the shape of RAG.

bought Ṁ50 YES

AIs have limited context window and if not that then limited memory. Therefore for efficient retrieval you need to reduce the amount of data fed to AI model. The best way to do that is some other form of retrieval.

„Agentic AIs“ would still be connected to some sort of retrieval.

Clarification welcome.
The goal is to assess whether companies building RAG engines are making good medium-term bets.

© Manifold Markets, Inc.Terms + Mana-only TermsPrivacyRules