轻量级动态检索生成系统，单卡运行仍高效完成复杂研究任务。
RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition
- 基于查询复杂度动态调整检索策略，实现智能资源分配
- 仅用消费级显卡支持复杂研究任务，性能优于同类系统
- 适合需要高效低耗的科研辅助工具开发者参考
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。提出一种名为路由到RAG（R2RAG）的研究型检索增强生成架构，由轻量组件构成，可根据推断出的查询复杂度和证据充分性动态调整检索策略。系统采用较小的大型语言模型，在单张消费级GPU上即可运行，同时支持复杂研究任务。该系统基于2025年ACM SIGIR LiveRAG挑战赛冠军G-RAG系统改进，并引入基于输出质量分析的模块优化。R2RAG在开源类别中获得最佳动态评估奖，证明了其在精心设计下兼具高效率与高性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。