RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition
This work addresses the need for efficient and effective RAG systems for research applications, building incrementally on prior award-winning systems.
The paper tackles the problem of improving retrieval-augmented generation (RAG) for complex research tasks by introducing the Routing-to-RAG (R2RAG) architecture, which dynamically adapts retrieval strategies based on query complexity and evidence sufficiency, and it won the Best Dynamic Evaluation award in the NeurIPS 2025 MMU-RAG Competition.
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.