PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving

arXiv:2609.10372 · cs.CV, cs.AI, cs.RO · Submitted 2026-09-09 · Read on arXiv

cs.CV, cs.AI, cs.RO

Submitted: 2026-09-09

Updated: 2026-09-10

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Perceived Time-to-First-Response — 1× in this paper
• RAG — 1× in this paper · explained in 3 episodes

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models