MMODELYST
Papers/RAISE: RAG Design as an Architecture Search Problem
PAP

RAISE: RAG Design as an Architecture Search Problem

May 28, 2026

arXiv
Abstract

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 support controlled and reproducible study of this problem, we introduce the RAG Intelligence Search Engine (RAISE), a comprehensive framework and benchmark for RAG hyperparameter optimization, which evaluates optimization methods for RAG pipelines under standardized search spaces and budgets. RAISE implements 13 search algorithms and evaluates them across seven public text and multimodal datasets using three random seeds. Our experiments show that optimization performance is highly task-dependent: methods that perform strongly on one dataset may not generalize consistently across others, cautioning against interpreting aggregate rankings as evidence of universally superior strategies. RAISE provides a common experimental substrate for fair, reproducible, and systematic research on RAG hyperparameter optimization.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Zhen Chen, Yibing Liu, Weihao Xie, Yu Liang, Peilin Chen, Shiqi Wang
Your notes (browser-local)
saved
arXiv:2605.30029