RAISE: RAG Design as an Architecture Search Problem

ArXi:2605.30029v1 Announce Type: new Retrieval-augmented generation (RAG) systems expose numerous design choices spanning query rewriting, chunking, retrieval depth, reranking, and context compression. In practice, these choices are often configured through heuristics, hindering systematic evaluation and reproducibility across settings. We argue that this challenge is best formulated as RAG architecture search. To controlled and reproducible study of this problem, we.