RMIT-ADM+S在MMU-RAG NeurIPS 2025比赛中的表现
RMIT-ADM+S at the MMU-RAG NeurIPS 2025 Competition
AI总结:
RMIT-ADM+S系统通过Routing-to-RAG架构在NeurIPS 2025 MMU-RAG比赛中获胜,实现了高效检索增强生成和复杂科研任务处理。
摘要:
本文介绍了在NeurIPS~2025 MMU-RAG比赛文本到文本赛道中获奖的RMIT-ADM+S系统。我们引入了Routing-to-RAG(R2RAG),一种专注于研究的检索增强生成(RAG)架构,由轻量级组件组成,能够根据推断的查询复杂性和证据充分性动态调整检索策略。该系统使用较小的LLM,使单个消费级GPU即可运行,同时支持复杂的科研任务。它基于ACM~SIGIR~2025 LiveRAG挑战的获奖G-RAG系统,并通过定性评估输出结果扩展了其模块。R2RAG在开源类别中赢得了最佳动态评估奖,证明了精心设计和高效资源利用的高有效性。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。