Networked ai systems enable adaptable intelligence with layered design
Networked AI: Architecture, Theory, and Applications
Artificial IntelligenceNetworking and Internet Architecture
Summary
Current AI methods usually train one big model on large, fixed datasets, which makes updating hard and slow. The authors propose Networked AI, where many smaller AI agents work together, learn continuously, and adapt to new situations. This design uses layers to organize how these agents interact, extract data, and evolve safely. Their approach improves efficiency and scale, allowing AI to better handle changing environments and specialize over time.
What this means in practice
- •For iot system engineers: Deploy networked AI agents for scalable and adaptive intelligence across heterogeneous IoT devices in dynamic environments.
- •For industrial automation teams: Implement hierarchical networked AI to enable continuous evolution and online adaptation of machine intelligence on factory floors.
- •For wireless infrastructure providers: Use Networked AI for autonomous collective intelligence to optimize cellular network resource management under variable conditions.$Commercial implications: Offers a novel scalable AI solution to improve cellular network performance, enabling sellable smart network management services.
Authors
Liang Song, Jiayue Jin, Peng Sun, Di Li, Yang Liu, Athanassios Skodras, Dimitris Ampeliotis, Yong Yuan, Amit Dvir, Jiangchuan Liu, Victor C. M. Leung, Qi Bi
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.