The Model in the Middle: Toward AI-Native Real-Time Communication

Ziqian Liu; Minghao Li; Yiming Qiu

Home/Archive/arXiv

arXiv · 2607.25792

The Model in the Middle: Toward AI-Native Real-Time Communication

Ziqian Liu·Minghao Li·Yiming Qiu

View original source ↗Read source document ↗Export metadata ↓

Abstract

Full-duplex omni models are transforming human--AI interaction from turn-based exchanges into continuous multimodal conversations in which speaking, listening, and reasoning unfold concurrently. Rather than viewing the model as a replacement for a human endpoint, we argue for a new perspective: the model is a stateful computational middlebox inside a human-centered feedback loop, with network transport, model serving, and user playback jointly shaping how the interaction evolves. This perspective breaks the traditional boundaries among stages designed around local objectives. Rather than optimizing them in isolation, an AI-native real-time stack should allow the state of each stage to shape the actions of the others. We explore three cross-stage coordination opportunities: network-aware inference scheduling, execution-aware transport prioritization, and playback control that accounts for both network and model variability. We are building Conflux to explore these ideas, and preliminary results show substantial improvements in response latency and playback deadline adherence under network degradation. More broadly, we call for an AI-native real-time communication stack that resolve the joint control problem spanning communication, computation, and playback.

Explore related subjects

cs.NI

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Ziqian Liu, Minghao Li, Yiming Qiu. 2026-07-28. The Model in the Middle: Toward AI-Native Real-Time Communication. https://arxiv.org/abs/2607.25792

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Decoding Delay Guarantees of Space Regulated Multiple Access Random Wireless Networks using Successive Interference Cancellation

This paper is focused on decoding delay guarantees in wireless networks, where messages have a given signal-to-interference-plus-noise ratio threshold $η_0$ to meet in order to be successfully decoded, and where transmissions should occur within some strict time constraints. Its main contribution consists in quantifying the worst-case transmissions decoding delays in the uplink of cellular and cell-free networks using successive interference cancellation. We show how such decoding delay guarantees can be obtained using spatial network calculus, a new tool introduced recently, and in particular spatial regulation. The results rely on the assumption of absence of fading. We nevertheless outline what this approach will lead to in the fading case for cellular networks.

cs.NI↗

arXiv2026

Toward Composable Network Digital Twins: A Subgraph-Based Latency Prediction Study

Modern networks must support changing topologies, configurations, and performance objectives, motivating fast and reliable performance estimation. Network digital twins (NDTs) enable what-if analysis for performance estimation in such network scenarios, however, existing machine learning-based NDT approaches often rely on entire topology representations, which are inherently monolithic and lack reusability under topological or traffic changes in the network. This paper introduces a composable NDT approach that decomposes networks into subgraphs represented by reusable unit twins that capture subgraph structure, configuration and traffic behaviours. A lightweight composer aggregates unit twin combinations to create NDTs that predict per-route end-to-end latency through an overall topology. Evaluation across controlled synthetic topologies and diverse traffic scenarios, real-world Topology Zoo topologies, and a public NDT challenge dataset demonstrates that the composable NDTs achieve high in-distribution accuracy while remaining stable under out-of-distribution scenarios. Comparison with monolithic full topology NDTs demonstrates that our composable approach achieves reusability, while achieving comparable or superior accuracy.

cs.NI↗

arXiv2026

Pattern-Aware Virtual Network Embedding Optimization for Cloud Data Centers

The network virtualization (NV) technology has enabled the sharing of multiple resources among virtual networks (VNs) in cloud data centers. One of the key challenges is to allocate resources in real-time for virtual network request (VNR), which is known as online virtual network embedding (VNE). However, the existing online VNE methods do not exploit the multi-dimensional complementary relationship among diverse VNRs, resulting in the fragmentation and waste of substrate resources. In this paper, we propose the pattern matching based online VNE approach by constructing appropriate matching rules among observed patterns to maximize resources utilization. We devise the clustering based VNRs quantization method and conduct rigorous study on the pattern combination filtering problem. Then, we utilize the column generation to solve it and construct the pattern matching rules. Based on the rules, we propose an online pattern matching VNE algorithm with linear worst-case complexity. Evaluation on a 106-server testbed using Alibaba production cluster trace dataset shows that our algorithm achieves close-to-offline performance and more accepted workloads that outperforms traditional designs by 25%-30%.

cs.NI↗