English

Cache Mechanism for Agent RAG Systems

Computation and Language 2025-11-06 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2511.02919,
  title  = {Cache Mechanism for Agent RAG Systems},
  author = {Shuhang Lin and Zhencan Peng and Lingyao Li and Xiao Lin and Xi Zhu and Yongfeng Zhang},
  journal= {arXiv preprint arXiv:2511.02919},
  year   = {2025}
}
R2 v1 2026-07-01T07:21:53.659Z