Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition

Kun Ran, Marwah Alaofi, Danula Hettiachchi, Chenglong Ma, Khoi Nguyen Dinh Anh, Khoi Vo Nguyen, Sachin Pathiyan Cherumanal, Lida Rashidi, Falk Scholer, Damiano Spina, Shuoqi Sun, Oleg Zendel

Abstract

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.

RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition

Abstract

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.
Paper Structure (22 sections, 1 equation, 1 figure)

This paper contains 22 sections, 1 equation, 1 figure.

Table of Contents

  1. Introduction
  2. Qualitative Evaluation
  3. System Architecture
  4. Query Classifier
  5. Vanilla RAG
  6. Vanilla Agent
  7. Deployment and Evaluation Infrastructure
  8. Conclusions
  9. Prompts
  10. Query Classifier
  11. System Prompt:
  12. User Prompt:
  13. Query Variants Generator
  14. System Prompt:
  15. User Prompt:
  16. ...and 7 more sections

Figures (1)

  • Figure 1: Overview of the system. The workflow includes a query classifier that routes each query to either a Vanilla RAG path for simple queries or a Vanilla Agent for complex queries that iteratively issues revised search query variants until sufficient evidence is gathered, followed by an answer generation module.