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.
@article{arxiv.2602.20735,
title = {RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition},
author = {Kun Ran and Marwah Alaofi and Danula Hettiachchi and Chenglong Ma and Khoi Nguyen Dinh Anh and Khoi Vo Nguyen and Sachin Pathiyan Cherumanal and Lida Rashidi and Falk Scholer and Damiano Spina and Shuoqi Sun and Oleg Zendel},
journal= {arXiv preprint arXiv:2602.20735},
year = {2026}
}