{"slug": "r-2-adapter-a-routing-and-rewriting-adapter-for-efficient-hybrid-rag", "title": "R$^{2}$Adapter: A Routing and Rewriting Adapter for Efficient Hybrid RAG", "summary": "Researchers introduced R²Adapter, a lightweight plug-in Routing and Rewriting Adapter that dynamically allocates queries between vanilla and graph-based Retrieval-Augmented Generation (RAG), reducing graph-based RAG usage by up to 59% while maintaining comparable answer accuracy on three multi-hop QA benchmarks. The model-agnostic adapter routes only queries that benefit from graph reasoning and rewrites uncertain graph-routed queries to improve retrieval quality without extra supervision.", "body_md": "arXiv:2609.02894v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/r-2-adapter-a-routing-and-rewriting-adapter-for-efficient-hybrid-rag", "canonical_source": "https://arxiv.org/abs/2609.02894", "published_at": "2026-09-04 04:00:00+00:00", "updated_at": "2026-09-04 04:22:03.958906+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-research", "ai-tools"], "entities": ["R²Adapter", "Retrieval-Augmented Generation (RAG)", "Large Language Models (LLMs)"], "alternates": {"html": "https://wpnews.pro/news/r-2-adapter-a-routing-and-rewriting-adapter-for-efficient-hybrid-rag", "markdown": "https://wpnews.pro/news/r-2-adapter-a-routing-and-rewriting-adapter-for-efficient-hybrid-rag.md", "text": "https://wpnews.pro/news/r-2-adapter-a-routing-and-rewriting-adapter-for-efficient-hybrid-rag.txt", "jsonld": "https://wpnews.pro/news/r-2-adapter-a-routing-and-rewriting-adapter-for-efficient-hybrid-rag.jsonld"}}