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

Abstract

We present the PACE, a framework for retrieval-augmented dialogue serving that formalizes Perceived Time-to-First-Response (PTFR) as a QoE objective and minimizes it under quality/cost constraints. Unlike prior work on cascaded routing, semantic caching, or adaptive retrieval, PACE jointly controls which answer source composes the response and what fills the waiting window. Deployed on a humanoid-robot sales service, it combines three mechanisms: a load-adaptive cascading router, a joint path-filler controller, and volatility-aware cache admission. On 75k CarQA requests, the cascade halves pure-LLM PTFR at P95 (0.29 vs 0.53s at c16). The adaptive controller reaches 0.41s P95, outperforming RAG by 2.4 times at high load with equal quality. The filler controller cuts calls by 94% with zero conflict. Volatility-aware admission reduces stale answers from 86% to 0%. A gating rule ensures the controller never worse than the baseline, with exposure bounded by one hold period. This is the first quantification of filler-answer conflict risk in deployed services.

Authors 7

Lin Huang, Yujuan Tan, Weisheng Li, Lixiang Zeng, Kun Yang, Yongzong Wang, Suihan Xiao

Specification

Official page: arxiv.org/abs/2609.10372
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
Arxiv announce type: replace
Source:arXiv (Atom API + RSS)T1observed 54 min agohigh
arXiv id: 2609.10372
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
Categories: cs.CV, cs.AI, cs.RO
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
PDF: arxiv.org/pdf/2609.10372
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
Primary category: cs.CV
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh
Published: 11 Sept 2026
Source:arXiv (Atom API + RSS)T1observed 55 min agohigh

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance

Attributed facts

9

Source tiers

T19

Freshest observation

54 min ago

Conflicts

None

No models linked to this paper yet.

Authors: Lin Huang, Yujuan Tan, Weisheng Li

As of

Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.

Claim history · arXiv id

1 claims · 1 propertiesShow all properties

arXiv idarxiv_id1

Claim history for arXiv id
Value	Valid from → to	Status	Source	Confidence	Extractor
2609.10372	11 Sept 2026 21:03 UTC → current	current	arXiv (Atom API + RSS)T1	high	deterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

11 Sept 2026
Property changedPaperPACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving
PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving: arxiv announce type changed from cross to replace
Arxiv announce typecross→replacearxiv
rss.arxiv.org
11 Sept 2026
New paperPaperPACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving
New paper: PACE: Perceived-Latency-Aware Cascading Service Routing and Filler Control for QoE-Efficient Retrieval-Augmented Dialogue Serving
arxiv
rss.arxiv.org

Full timeline →

Source documents
Source	Document	Type	Tier	Last observed	Snapshots
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.CV	feed	T1· Official	54 min ago	1
arXiv (Atom API + RSS)	rss.arxiv.org/rss/cs.AI	feed	T1· Official	54 min ago	1

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.