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.
@article{arxiv.2603.02206,
title = {VoiceAgentRAG: Solving the RAG Latency Bottleneck in Real-Time Voice Agents Using Dual-Agent Architectures},
author = {Jielin Qiu and Jianguo Zhang and Zixiang Chen and Liangwei Yang and Ming Zhu and Juntao Tan and Haolin Chen and Wenting Zhao and Rithesh Murthy and Roshan Ram and Akshara Prabhakar and Shelby Heinecke and Caiming Xiong and Silvio Savarese and Huan Wang},
journal= {arXiv preprint arXiv:2603.02206},
year = {2026}
}