# R$^3$AG: Retriever Routing for Retrieval-Augmented Generation

Source: [R$^3$AG: Retriever Routing for Retrieval-Augmented Generation](<https://www.sota2.com/research/paper/69f03f0c55a3c32af89f9fdb>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-29T05:00:05.003Z

Authors: Tong Zhao, Yutao Zhu, Yucheng Tian, Zhicheng Dou

Published: 2026-04-22T06:51:20.000Z

## Abstract

Retrieval-augmented generation (RAG) has become a cornerstone for knowledge-intensive tasks. However, the efficacy of RAG is often bottlenecked by the \`\`one-size-fits-all'' retrieval paradigm, as different queries exhibit distinct preferences for different retrievers. While recent routing techniques attempt to select the optimal retriever dynamically, they typically operate under a \`\`single and static capability'' assumption, selecting retrievers solely based on semantic relevance. This overlooks a critical distinction in RAG: a retrieved document must not only be relevant but also effectively support the generator in producing correct answers. To address this limitation, we propose R$^3$AG, a novel routing framework that explicitly models the dynamic alignment between queries and retriever capabilities. Unlike previous approaches, R$^3$AG decomposes retriever capability into two learnable dimensions: retrieval quality and generation utility. We employ a contrastive learning objective that leverages complementary supervision signals, \\textit{i.e.}, document assessments and downstream answer correctness, to capture query-specific preference shifts. Extensive experiments on several knowledge-intensive tasks show that R$^3$AG consistently outperforms both the best individual retrievers and state-of-the-art static routing methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Question Answering on HotpotQA (test) (EM and F1 Metrics)](<https://www.sota2.com/research/sota/question-answering-on-hotpotqa-test-em-and-f1-metrics.md>): Question Answering; HotpotQA (test); EM: 29.13.

- [Question Answering on NQ (test)](<https://www.sota2.com/research/sota/question-answering-on-nq-test.md>): Question Answering; NQ (test); EM Accuracy: 37.81.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.22849>)

[PDF](<https://arxiv.org/pdf/2604.22849.pdf>)