Artificial Intelligence of Things as a Foundation for Agentic AI Systems: Architectures, Applications, and Challenges
Искусственный интеллект вещей как основа агентных систем искусственного интеллекта: архитектуры, приложения и проблемы
2026-06-15
SCID: 54.1/xdr3hbkr
Discuss with AI
Artificial Intelligence of Thingsagentic AI systemsdigital twinsedge intelligencesemantic communication
Figures from the paper
Abstract (AI)
The evolution of Artificial Intelligence (AI) has reached a critical point, where agentic AI systems demonstrate strong capabilities in goal formulation and planning but remain difficult to deploy in real-world settings due to their limited grounding in physical environments. These limitations arise from the challenges of partial observability, actuation uncertainty, and strict resource constraints that characterize the physical world. This survey argues that the Artificial Intelligence of Things (AIoT) provides the necessary foundation to embed agentic intelligence into such environments by enabling continuous interaction between sensing, reasoning, and action. We analyze the synergy between goal-driven agentic AI and distributed AIoT infrastructures and present a unified taxonomy of AIoT-enabled agentic architectures, highlighting trade-offs across centralized, edge-native, and hybrid deployment models. The survey further examines key enabling technologies, including edge intelligence, semantic communication, digital twins, and trust mechanisms, and discusses how they integrate into cognitive control loops. Through representative applications in smart cities, industrial automation, healthcare, and energy systems, we show how this convergence moves automation beyond rule-based behavior toward context-aware autonomy. Finally, we identify open challenges related to long-horizon safety, resource-aware intelligence, and ethical governance, and outline research directions toward robust, trustworthy, and socially embedded autonomous systems.
Key Findings
1
AIoT is presented as a foundational infrastructure for grounding agentic AI in physical environments through continuous sensing, reasoning, and action.
2
AIoT–agentic AI convergence enables context-aware autonomy beyond rule-based automation across smart cities, industrial automation, healthcare, and energy systems.
3
Edge intelligence, semantic communication, digital twins, and trust mechanisms are identified as key technologies for integrating agentic reasoning into cognitive control loops.
4
Major unresolved challenges include long-horizon safety, resource-aware intelligence, and ethical governance for robust and socially embedded autonomous systems.
5
The survey develops a unified taxonomy of AIoT-enabled agentic architectures, comparing centralized, edge-native, and hybrid deployment trade-offs.
Research Object
AIoT-enabled agentic AI systems operating in physical environments
Research Subject
Architectures, enabling technologies, deployment trade-offs, and challenges for grounding agentic intelligence in physical environments
Publication Details
Publication Date
2026-06-15
Journal
Publisher
ISSN
Cited by
3
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest