cs.AIMay 28, 2026

RAISE: RAG Design as an Architecture Search Problem

Authors: Zhen ChenYibing LiuWeihao XieYu LiangPeilin ChenShiqi Wang

Organizations: City University of Hong Kong, Hong Kong SAR · Baidu Inc.

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.

Explore similar work

CardsList
  1. RAG-Stack: Co-Optimizing RAG Serving Performance and Quality

    Aug 4, 2026Haiqiang Zhang, Yuanqing Lei, Wanting Li +2Pareto Frontier