This paper presents the award-winning RMIT-ADM+S system for the Text-to-Text track of the NeurIPS~2025 MMU-RAG Competition. We introduce Routing-to-RAG (R2RAG), a research-focused retrieval-augmented generation (RAG) architecture composed of lightweight components that dynamically adapt the retrieval strategy based on inferred query complexity and evidence sufficiency. The system uses smaller LLMs, enabling operation on a single consumer-grade GPU while supporting complex research tasks. It builds on the G-RAG system, winner of the ACM~SIGIR~2025 LiveRAG Challenge, and extends it with modules informed by qualitative review of outputs. R2RAG won the Best Dynamic Evaluation award in the Open Source category, demonstrating high effectiveness with careful design and efficient use of resources.

翻译：本文介绍了在 NeurIPS 2025 MMU-RAG 竞赛文本到文本赛道中获奖的 RMIT-ADM+S 系统。我们提出了 Routing-to-RAG（R2RAG），这是一种专注于研究的检索增强生成架构，由轻量级组件构成，能够根据推断的查询复杂性和证据充分性动态调整检索策略。该系统使用较小的 LLM，使其能够在单张消费级 GPU 上运行，同时支持复杂的研究任务。它基于曾赢得 ACM SIGIR 2025 LiveRAG 挑战赛的 G-RAG 系统构建，并通过基于输出定性分析而设计的模块对其进行了扩展。R2RAG 在开源类别中获得了最佳动态评估奖，证明了通过精心设计和高效利用资源可以实现高效能。