The LLM RAG Obituary: Killed by Agents, Buried by Context Windows

Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by bjornsing on Thursday October 02, 2025 @02:19AM (#45446808)

But couldn’t an LLM search for documents in that enterprise knowledge base just like humans do, using the same kind of queries and the same underlying search infrastructure?

[ Parent | on HN ]

Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by z3dd on Thursday October 02, 2025 @02:53AM (#45446961)

I wouldn't say humans are efficient at that so no reason to copy, other than as a starting point.

[ Parent | on HN ]

Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by carlmr on Thursday October 02, 2025 @03:35AM (#45447160)

Maybe not efficient, but if the LLMs can't even reach this benchmark then I'm not sure.

[ Parent | on HN ]

Re:The LLM RAG Obituary: Killed by Agents, Buried by Context... by zwaps on Thursday October 02, 2025 @04:10AM (#45447309)

Yes but that would be worse than many RAG approaches, which were implemented precisely because there is no good way to cleanly search through a knowledge base for a million different reasons.

At that point, you are just doing Agentic RAG, or even just Query Review + RAG.

I mean, yeah, agentic RAG is the future. It's still RAG though.

[ Parent | on HN ]