arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.02206cs.SD
收藏

VoiceAgentRAG: 通过双代理架构解决实时语音代理中RAG的延迟瓶颈

VoiceAgentRAG: Solving the RAG Latency Bottleneck in Real-Time Voice Agents Using Dual-Agent Architectures

Salesforce AI Research(Salesforce人工智能研究)
Jielin Qiu, Jianguo Zhang, Zixiang Chen, Liangwei Yang, Ming Zhu, Juntao Tan, Haolin Chen, Wenting Zhao, Rithesh Murthy, Roshan Ram, Akshara Prabhakar, Shelby H… 展开作者

Jielin Qiu, Jianguo Zhang, Zixiang Chen, Liangwei Yang, Ming Zhu, Juntao Tan, Haolin Chen, Wenting Zhao, Rithesh Murthy, Roshan Ram, Akshara Prabhakar, Shelby Heinecke, Caiming Xiong, Silvio Savarese, Huan Wang

AI总结:

VoiceAgentRAG通过双代理架构实现实时语音代理中RAG的延迟优化,利用预加载缓存提升检索效率。

摘要:

我们提出了VoiceAgentRAG,一种开源的双代理记忆路由器,将检索与响应生成解耦。一个背景Slow Thinker代理持续监控对话流,利用LLM预测可能的后续话题,并将相关文档片段预加载到基于FAISS的语义缓存中。一个前景Fast Talker代理只从这个亚毫秒级缓存中读取,在缓存命中时完全绕过向量数据库。

英文摘要:

We present VoiceAgentRAG, an open-source dual-agent memory router that decouples retrieval from response generation. A background Slow Thinker agent continuously monitors the conversation stream, predicts likely follow-up topics using an LLM, and pre-fetches relevant document chunks into a FAISS-backed semantic cache. A foreground Fast Talker agent reads only from this sub-millisecond cache, bypassing the vector database entirely on cache hits.

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。

↑