Networked AI: Architecture, Theory, and Applications

Liang Song; Jiayue Jin; Peng Sun; Di Li; Yang Liu; Athanassios Skodras; Dimitris Ampeliotis; Yong Yuan

cs.AINov 2, 2026

Networked AI: Architecture, Theory, and Applications

Authors: Liang Song, Jiayue Jin, Peng Sun, Di Li, Yang Liu, Athanassios Skodras, Dimitris Ampeliotis, Yong Yuan,

Organizations: College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai 200433, China · International Networking Systems of Artificial Intelligence Limited, Macao · Division of Natural and Applied Sciences, Duke Kunshan University, Kunshan 215316, China · Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo 315000, China · College of Electronic and Information Engineering, Tongji University, Shanghai 201804, China · Department of Electrical and Computer Engineering, University of Patras, Patras 26504, Greece · Department of Digital Media and Communication, Ionian University, Argostoli 28100, Greece · China Telecom Research Institute, Beijing 102218, China · Department of Computer Science, Ariel University, Ariel 40700, Israel · School of Computing Science, Simon Fraser University, Burnaby, BC V5A 1S6, Canada · Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC V6T 1Z4, Canada

Abstract

Recent advances in Artificial Intelligence (AI), particularly large-scale deep learning, have been driven by monolithic or offline training on massive curated datasets. While successful, these approaches face structural limitations: escalating data and computational demands, limited online adaptability, and a lack of system-level intelligence in open, non-stationary environments. This paper presents Networked AI - a networked intelligent system composed of interacting, heterogeneous, and continuously evolving AI agents. We establish a hierarchical layered architecture comprising an Agent Layer for heterogeneous capability construction, an Interaction Layer for signal-processing-guided online data extraction, and a Regulation Layer for stability-constrained collective evolution. Foundations in data science, signal processing, and system control are hereby synthesized into a unified theoretical framework of Networked AI, providing superior data efficiency, intelligence efficiency, interpretability, and scalability. Theoretical and experimental analysis demonstrates that Networked AI can approach near-linear scaling in resource demand, in contrast to the exponential increase in standalone end-to-end systems. It provides not only online adaptation to out-of-distribution environmental novelties, but also the autonomous evolution towards application-specific intelligence. Application frontiers are discussed for IoT spaces, embodied, spatial, and industrial intelligences, as well as the cellular infrastructure and beyond. Key open challenges are identified towards realizing locally autonomous, collectively intelligent, continuously evolving, globally regulated Networked AI.

Figures & tables

Fig. 1: Layered architecture of Networked AI.

Symbol	Definition / Description
$\mathcal{A}$	Universal set of all heterogeneous intelligent entities
$N$	Total number of agents in the network
$a$	An individual autonomous intelligent agent
$\mathcal{X},\mathcal{Y}$	Input and output spaces of an agent (respectively)
$\Theta$	Internal model parameters or rule set of an agent
$\Pi$	Specific update mechanism / learning paradigm of an agent

TABLE I: Nomenclature of the Networked AI Framework

Panel of Figure 3 — Fig. 2: Computational cost to convergence under different model, application and overall task complexity scales. The box plots summarize the variability across heterogeneous experimental configurations, while the solid and dashed curves represent the global power-law or exponential fits for standalone AI and Networked AI.

Paradigm	Intelligence Source	Data Source	Adaptation	Coordination	Scalability
Expert Systems	Human Rules	Knowledge Bases	None	None	Low
Deep Learning	Model Parameters	Labeled Datasets	Offline	None	Moderate
Foundation Models	Large-scale Pretraining	Web-scale Data	Limited	None	Compute-Bounded
Multi-Agent AI	Agent Cooperation	Environment Interaction	Partial	Explicit	Moderate
Networked AI	Collective Evolution	Knowledge and Operation Data	Online Evolutive	Adaptive + Regulated	Hierarchical and Near-linear

TABLE II: Paradigm Migrations Toward Networked AI.

AI Agent Architecture

See all 37 papers

The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scale
Jun 11, 2026Quanyan ZhuMulti-Agent Coordination Multi-Agent Orchestration
Department of Electrical and Computer Engineering and the NYU Center for Cybersecurity, NYU Tandon School of Engineering, New York University, Brooklyn, NY 11201, USA.
AI-Model Network: Concept, Current State and Future
May 25, 2026Li Zhetao, Zeng Xiyu, Wang Jianhui +6
（College of information science and technology, Jinan University, Guangzhou 510632）
Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Design
May 1, 2026Seyed Mohammad Azimi-Abarghouyi, Mehdi Bennis, Leandros TassiulasHierarchical Federated Learning Communication-Efficient Distributed Training
Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden · Centre for Wireless Communications, University of Oulu, Oulu, Finland · Department of Electrical Engineering, Yale University, New Haven, USA

Jun 11, 2026J/K move · Enter open · S save

The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scale

Quanyan Zhu

Department of Electrical and Computer Engineering and the NYU Center for Cybersecurity, NYU Tandon School of Engineering, New York University, Brooklyn, NY 11201, USA.

Multi-Agent Coordination Multi-Agent Orchestration AI Agent Governance Multi-Agent Communication Agentic AI

Open paper AskPDF arXiv

The rapid emergence of autonomous AI agents is transforming artificial intelligence from isolated model inference into distributed systems of reasoning, communication, and action. This paper develops the vision of the Internet of Agentic AI (IoAI): an open ecosystem in which heterogeneous agents discover one another, negotiate responsibilities, exchange context, invoke tools, and execute workflows across cloud, edge, device, organizational, and cyber-physical environments. We synthesize foundations from single-agent agentic AI, multi-agent systems, distributed computing, communication networks, game theory, and security engineering to characterize the architectures and mechanisms required for scalable agent ecosystems. The paper examines agent deployment models, workflow lifecycles, communication protocols, interoperability layers, resource-management challenges, and trust architectures, with case studies in adaptive manufacturing and distributed operational coordination. The resulting framework highlights the central research challenges of controlled emergence, semantic interoperability, secure identity, incentive-compatible coordination, resource-aware orchestration, and governance for large-scale networks of autonomous agents.

Abstract

AI Agent Architecture

Explore similar work

The Internet of Agentic AI: Communication, Coordination, and Collective Intelligence at Scale

AI-Model Network: Concept, Current State and Future

Hierarchical Federated Learning for Networked AI: From Communication Saving to Architecture-Aware Design