arXivLin Huang, Yujuan Tan, Weisheng Li, Lixiang Zeng, Kun Yang, Suihan XiaoWed, Sep 9, 2026, 9:02 AM PDT
score 17.1
Router Cuts Chatbot Wait Times Using Smart Answer Filler
Original: PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving
Source: arxiv.org ↗
Writing ELI5 summary…