Skip to content
AI News HubLIVE
Original source2 min read

R²Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG

Summary

Researchers propose R²Adapter, a lightweight plug-in routing and rewriting adapter that dynamically allocates queries between vanilla and graph-based RAG. Experiments on multi-hop QA benchmarks show up to 59% reduction in graph-based RAG usage while maintaining comparable answer accuracy.

SourcearXiv Computational LinguisticsAuthor: Yucan Guo, Miao Su, Saiping Guan, Long Bai, Zhongni Hou, Zixuan Li, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng
R²Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 1 Jul 2026]

Title:R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG

View a PDF of the paper titled R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG, by Yucan Guo and 8 other authors

View PDF HTML (experimental)

Abstract:Retrieval-Augmented Generation (RAG) has become a prevailing paradigm for enhancing Large Language Models (LLMs) with non-parametric knowledge. Vanilla RAG efficiently handles simple queries but struggles with relational or multi-hop reasoning. Graph-based RAG alleviates this issue but incurs higher inference complexity and latency. In practice, user queries can differ significantly in their complexity, rendering a fixed RAG strategy suboptimal. However, existing hybrid text-graph RAG methods typically rely on heuristic and LLM-based routing, resulting in unnecessary overhead and strong dependence on the underlying LLM. To address these challenges, we propose R$^{2}$Adapter, a lightweight plug-in Routing and Rewriting Adapter designed to allocate queries between vanilla and graph-based RAG dynamically. By routing only the queries that genuinely benefit from graph-based reasoning, R$^{2}$Adapter reduces unnecessary graph retrieval overhead. Additionally, uncertain graph-routed queries are rewritten to better expose their multi-hop reasoning requirements, improving retrieval quality without additional supervision. Extensive experiments on three multi-hop QA benchmarks demonstrate that R$^{2}$Adapter reduces graph-based RAG usage by up to 59% while maintaining comparable answer accuracy. This adapter is model-agnostic and can be seamlessly integrated into diverse vanilla and graph-based RAG pipelines, providing an efficient and adaptive solution for hybrid RAG systems.

Subjects:

Computation and Language (cs.CL); Information Retrieval (cs.IR)

Cite as: arXiv:2609.02894 [cs.CL]

(or arXiv:2609.02894v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2609.02894

arXiv-issued DOI via DataCite

Submission history

From: Yucan Guo [view email] [v1] Wed, 1 Jul 2026 09:08:03 UTC (581 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG, by Yucan Guo and 8 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-09

Change to browse by:

cs cs.IR

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • R²Adapter routes queries dynamically between vanilla and graph-based RAG, using graph retrieval only when it genuinely benefits reasoning.
  • Uncertain graph-routed queries are rewritten to better expose multi-hop requirements without additional supervision.
  • Across three multi-hop QA benchmarks, graph-based RAG usage drops by up to 59% with comparable answer accuracy.
  • The model-agnostic adapter integrates seamlessly into diverse vanilla and graph-based RAG pipelines.

Highlights and analysis are generated automatically and may contain errors. Check the original source.