Problem
Research questions and friction points this paper is trying to address.
Internet of Agentic Things
closed-loop orchestration
cyber-physical systems
autonomous AI agents
trustworthy deployment
Internet of Agentic Things: Networked AI Agents for Closed-Loop IoT Orchestration
🤖 AI Summary
This work addresses the challenge of achieving efficient coordination among perception, decision-making, and actuation in Internet of Things (IoT) systems operating in complex dynamic environments. To this end, the paper proposes the Internet of AI Things (IoAT) architecture, which for the first time deeply integrates agent-based AI, digital twins, edge computing, and physical AI to establish a closed-loop collaborative mechanism across cloud, edge, and end devices. The authors innovatively design a nested strategic–tactical decision-making framework based on morphogenetic dynamic programming and incorporate formalized workflow control to enable autonomous cross-layer coordination. The efficacy of the proposed architecture is validated in a smart building scenario, and the study further provides a systematic analysis of critical challenges concerning security, governance, resilience, and trustworthy deployment.
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Internet of Agentic Things
agentic AI
closed-loop orchestration
hylomorphic dynamic programming
cyber-physical systems
🔎 Similar Papers
💼 Related Jobs
