mlsanityData to 14 Oct 2026

Coordinated Networking for On-Device Agent-Augmented Real-Time Communication

arXiv 2607.22854 ↗First posted 24 Jul 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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%.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 20 of its 65 references that are in the map. First posted on arXiv 24 Jul 2026.

Builds on

20 of 65 references.

References · 20

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2025Qwen2.5-VL Technical Reportcited by 5,587
  4. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,141
  5. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  6. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,417
  7. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  8. 2024DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Servingcited by 617
  9. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 365
  10. 2025Small Language Models are the Future of Agentic AIcited by 270
  11. 2024CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusioncited by 223
  12. 2023PowerInfer: Fast Large Language Model Serving with a Consumer-grade GPUcited by 217
8 more
  1. 2023CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Servingcited by 203
  2. 2024Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttentioncited by 163
  3. 2025KVzip: Query-Agnostic KV Cache Compression with Context Reconstructioncited by 95
  4. 2023Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipelinecited by 86
  5. 2023S3: Increasing GPU Utilization during Generative Inference for Higher Throughputcited by 81
  6. 2025Autellix: An Efficient Serving Engine for LLM Agents as General Programscited by 58
  7. 2025The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspectivecited by 39
  8. 2025Scalable Video Conferencing Using SDN Principlescited by 1

Built on by

Not cited yet.