Metraipolis › archive › dc_9cf7ee4ee1bd

R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG — arXiv:2609.02894

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.02894
License (as archived)
CC0-1.0
Archived
2026-10-17T01:37:16.935Z
SHA-256 of the archived text
fb091eeb273c07466bcb9d116bf53f2962332fa6fe291735c801091a0b77789e
Stable URL of this page
https://metraipolis.com/documento/dc_9cf7ee4ee1bd

How to cite

R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG — arXiv:2609.02894 — arXiv (en), https://arxiv.org/abs/2609.02894 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9cf7ee4ee1bd (Metraipolis archive dc_9cf7ee4ee1bd, sha256 fb091eeb273c07466bcb9d116bf53f2962332fa6fe291735c801091a0b77789e)
BibTeX
@misc{dc9cf7ee4ee1bd,
  title = {R$^2$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG — arXiv:2609.02894},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02894},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9cf7ee4ee1bd; sha256 fb091eeb273c07466bcb9d116bf53f2962332fa6fe291735c801091a0b77789e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02894. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.02894 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T01:11:43.481Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).