为智能体RAG系统设计动态缓存机制，显著提升检索效率与准确性。
Cache Mechanism for Agent RAG Systems
- 基于查询历史与嵌入空间几何，自动构建高相关性小规模缓存
- 仅需原数据集0.015%存储量，答对率达79.8%，延迟降低80%
- 无需人工标注，适用于需要高效知识访问的智能体应用
基于大语言模型的智能体发展得益于检索增强生成（RAG）技术，使模型能够访问庞大的外部知识库。尽管RAG在提升智能体性能方面取得成功，但针对每个智能体动态构建、维护和更新紧凑且相关的知识语料库的缓存管理仍缺乏研究。为此，我们提出ARC（Agent RAG Cache Mechanism），一种无需标注的新型缓存框架，可为每个智能体动态管理小规模、高价值的知识语料库。通过融合历史查询分布模式与嵌入空间中缓存项的内在几何结构，ARC能自动维护高相关性缓存。在三个检索数据集上的综合实验表明，ARC将存储需求降至原始语料库的0.015%，同时实现最高79.8%的有答案率，并将平均检索延迟降低80%。结果表明，ARC能显著提升基于RAG的大语言模型智能体的效率与效果。
原文摘要 · Abstract (English)
Recent advances in Large Language Model (LLM)-based agents have been propelled by Retrieval-Augmented Generation (RAG), which grants the models access to vast external knowledge bases. Despite RAG's success in improving agent performance, agent-level cache management, particularly constructing, maintaining, and updating a compact, relevant corpus dynamically tailored to each agent's need, remains underexplored. Therefore, we introduce ARC (Agent RAG Cache Mechanism), a novel, annotation-free caching framework that dynamically manages small, high-value corpora for each agent. By synthesizing historical query distribution patterns with the intrinsic geometry of cached items in the embedding space, ARC automatically maintains a high-relevance cache. With comprehensive experiments on three retrieval datasets, our experimental results demonstrate that ARC reduces storage requirements to 0.015% of the original corpus while offering up to 79.8% has-answer rate and reducing average retrieval latency by 80%. Our results demonstrate that ARC can drastically enhance efficiency and effectiveness in RAG-powered LLM agents.
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。