Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2511.02919 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915598657650688 |
|---|---|
| author | Lin, Shuhang Peng, Zhencan Li, Lingyao Lin, Xiao Zhu, Xi Zhang, Yongfeng |
| author_facet | Lin, Shuhang Peng, Zhencan Li, Lingyao Lin, Xiao Zhu, Xi Zhang, Yongfeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_02919 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Cache Mechanism for Agent RAG Systems Lin, Shuhang Peng, Zhencan Li, Lingyao Lin, Xiao Zhu, Xi Zhang, Yongfeng Computation and Language 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. |
| title | Cache Mechanism for Agent RAG Systems |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2511.02919 |