Internet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Quanyan Zhu
• Venue: arXiv: cs.AI
• Published: 2026-07-14
• Collected: 2026-07-15
• URL: http://arxiv.org/abs/2607.12662v1
• PDF: https://arxiv.org/pdf/2607.12662v1
• DOI: UNKNOWN

Plain-Language Brief

The paper presents the Internet of Agentic Things (IoAT), a framework that combines AI agents, IoT, cyber-physical systems, edge computing, digital twins, and more to create a unified system for closed-loop IoT orchestration. The framework uses autonomous AI agents to connect different layers and manage decision-making in distributed cyber-physical environments.

What the Document Says

• The paper introduces the Internet of Agentic Things (IoAT).
• The IoAT integrates agentic AI, IoT, cyber-physical systems, Physical AI, edge computing, and digital twins.
• The architecture consists of cloud, edge/fog, and physical IoT layers.
• Connections between layers are made through autonomous AI agents that can perceive, reason, coordinate, and actuate across distributed cyber-physical environments.
• The paper formalizes IoAT as a coupled workflow-control problem with nested strategic and tactical decision making.
• The hylomorphic dynamic programming framework links agentic planning with physical execution.

Key Concepts Mentioned

• Internet of Agentic Things (IoAT)
• agentic AI
• IoT
• cyber-physical systems
• Physical AI
• edge computing
• digital twins
• autonomous AI agents

Claims Made by the Document

• The IoAT can create a unified system for closed-loop IoT orchestration.

Evidence Used

• The paper presents the architecture and framework for IoAT.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

The paper introduces the Internet of Agentic Things (IoAT), an architectural framework that integrates agentic AI, IoT, cyber-physical systems, Physical AI, edge computing, and digital twins into a unified closed-loop orchestration framework. The proposed architecture consists of cloud, edge/fog, and physical IoT layers connected through autonomous AI agents that perceive, reason, coordinate, and actuate across distributed cyber-physical environments. The paper formalizes IoAT as a coupled workflow-control problem with nested strategic and tactical decision making using a hylomorphic dynamic programming framework that links agentic planning with physical execution. Smart-building orchestration is presented as a representative use case, and key research challenges related to safety, security, governance, resilience, and trustworthy deployment are discussed.