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

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.

arXiv:2609.02894v1 Announce Type: new 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.