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
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。