跳到正文
arXiv cs.AI· Zexin Li, Xueyi Zhang, Tao Ren, Yiming Chen·· 4 小时前AI 评分35

A$^3$:面向协同边缘计算的自适应音频智能体框架

A$^3$: Adaptive Audio Agent Framework for Collaborative Edge Computing

AI 导读

arXiv 论文提出 A$^3$ 自适应音频智能体框架,将完整流水线阶段部署在边缘服务器,同时在设备端保留完整的回退智能体,并用链路感知截止时间决定何时放弃服务器。在 Jetson 设备与 RTX A4500 服务器上,A$^3$ 在链路正常时匹配纯服务器方案的表现,AGX 设备在全断连时仍能应答所有请求,并在模拟断连中优于百分位对冲方案。

正文 · 原文

View PDF HTML (experimental)

Abstract:Embedded audio agents need a nearby edge server for speed, but a server-dependent agent returns nothing when the link fails. We present A$^3$, an adaptive audio agent framework that places whole pipeline stages on the server, keeps a complete fallback agent on devices that can host one, and hedges both paths with a link-aware deadline that decides when to give up on the server. On Jetson devices and an RTX A4500 server, A$^3$ matches the server-only agent on a healthy link, answers every request in a full outage on the AGX, and beats a percentile hedge in simulated outages.
Subjects: Artificial Intelligence (cs.AI)
Cite as: arXiv:2611.18064 [cs.AI]
  (or arXiv:2611.18064v1 [cs.AI] for this version)
  https://doi.org/10.48550/arXiv.2611.18064

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Zexin Li [view email]
[v1] Fri, 13 Nov 2026 11:48:16 UTC (875 KB)

来源:arXiv cs.AI · arxiv.org