LLM Memory & RAG 相关度: 9/10

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
arXiv: 2602.20735v1 发布: 2026-02-24 更新: 2026-02-24
下载 PDF arXiv 页面

AI 摘要

RMIT-ADM+S团队提出R2RAG，一种动态调整检索策略的RAG架构，并在NeurIPS 2025竞赛中获奖。

主要贡献

  • 提出Routing-to-RAG (R2RAG)架构
  • 动态调整检索策略
  • 高效利用资源的小型LLM实现

方法论

R2RAG基于G-RAG系统，通过推断查询复杂度和证据充分性，动态调整检索策略，使用小型LLM。

原文摘要

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.

标签

RAG Retrieval-Augmented Generation Dynamic Retrieval

arXiv 分类

cs.IR cs.AI cs.CL