发表机构
Seoul National University; Microsoft Research Asia（首尔国立大学; 微软亚洲研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究设备上代理增强实时通信中的网络挑战，设计HFS框架，采用应用引导的多流传输方法，实现高视频质量和低代理响应延迟，相比基线，视频质量提高1.5倍，代理响应时间减少31%。
AI 中文摘要
人工智能代理正在开启代理增强实时通信（RTC）的新范式，人类专注于高级协作，代理实时自主检索、分析和生成信息以支持交互。现有基于云的代理存在隐私风险和不可扩展的服务器成本，设备上代理增强的RTC提供了有前景的替代方案。但该范式带来新网络挑战：人类（用于实时视频流）和代理（用于发送分析上下文文件）并发流量之间的争用。我们设计了HFS框架，通过应用引导的多流传输方法，统一的应用层编排器根据异构应用需求联合控制实时视频和代理上下文流的发送速率，确保高实时视频质量和低代理响应延迟。基于WebRTC构建的原型表明，HFS优于基线，视频质量提高1.5倍，同时代理响应时间减少31%。
英文摘要
AI agents are enabling a new paradigm of agent-augmented real-time communication (RTC), where humans focus on high-level collaboration, while agents autonomously retrieve, analyze, and generate information in real time to support their interactions. These apps enable new experiences across various domains: for example, when corporate employees co-author a legal document, their agents can discuss and draft on their behalf, sparing them the burden of manually reviewing each other's work. As existing cloud-based agents suffer from privacy risks and unscalable server costs, on-device agent-augmented RTC offers a promising alternative. However, this on-device paradigm introduces a new networking challenge: contention between concurrent traffic flows generated by humans (for live video streaming) and agents (for sending context files for analysis). We design HFS, a framework to ensure both high live video quality and low agent response latency in agent-augmented RTC apps. We achieve the goal through an app-guided multi-flow transport approach, where a unified app-layer orchestrator jointly controls the sending rates of live video and agent context flows based on their heterogeneous app requirements. Our prototype built atop WebRTC and llama.cpp demonstrates that HAFS outperforms baselines, achieving 1.5x higher video quality while reducing agent response time by 31%.
CommentsAccepted to USENIX NSDI 2027
