Integrating agentic AI and digital twins for intelligent decision-making systems
Интеграция агентного искусственного интеллекта и цифровых двойников для интеллектуальных систем принятия решений
2026-02-20
SCID: 54.1/bncfgzdd
Discuss with AI
LLM-based reasoningagentic AIclosed-loop autonomydigital twinspower grid management
Figures from the paper
Abstract (AI)
The integration of agentic artificial intelligence (agentic AI) and digital twins (DTs) enables decision-making systems that are intelligent, adaptive, and goal-oriented. This paper advances that convergence through a multilayer integration framework that organizes perception, knowledge and data management, LLM-based reasoning, learning, decision-making, action execution, and feedback adaptation into a cohesive structure. Within this framework, LLM-driven agents act as cognitive cores for context-aware planning and collaboration, while the digital twin provides a shared situational model that maintains real-time state, simulation capabilities, and policy constraints. The contributions are threefold: (i) a novel architecture that operationalizes continuous learning and closed-loop autonomy through tightly coupled agents and a DT; (ii) a use-case demonstration in power balancing for electrical grid management, where agents coordinate demand forecasting, distributed energy resources, and network constraints via a grid digital twin; and (iii) an analysis of key enablers and challenges, such as model synchronization, interpretability, safety, and cognitive load distribution, necessary for scalable and trustworthy deployment. The proposed integration offers a principled path to resilient, transparent, and data-efficient decision-making systems for cyber–physical infrastructure and provides a foundation for extending agentic AI-DT synergies to other safety-critical domains. • Integrates agentic AI with digital twins for adaptive decision-making. • Uses LLMs as cognitive cores for reasoning and goal-oriented autonomy. • Enables continuous learning through real-time feedback and simulation.
Key Findings
1
A multilayer framework integrates perception, data and knowledge management, LLM reasoning, learning, decisions, actions, and feedback adaptation.
2
A power-balancing use case coordinates demand forecasting, distributed energy resources, and network constraints through a grid digital twin.
3
LLM-driven agents provide context-aware planning and collaboration, while digital twins maintain shared real-time states, simulations, and policy constraints.
4
Scalable and trustworthy deployment depends on model synchronization, interpretability, safety, and effective cognitive-load distribution.
5
The tightly coupled architecture enables closed-loop autonomy and continuous learning through real-time feedback and simulation.
Research Object
agentic AI–digital twin integrated decision-making systems, demonstrated in electrical grid power balancing
Research Subject
adaptive, goal-oriented, closed-loop decision-making enabled by LLM-driven agents and real-time digital-twin state, simulation, feedback, and policy constraints
Publication Details
Publication Date
2026-02-20
Journal
Publisher
ISSN
Cited by
26
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai4
Digital Twin: Enabling Technologies, Challenges and Open Research2020
Digital Twin: Values, Challenges and Enablers From a Modeling Perspective2020
A Survey on AI-Driven Digital Twins in Industry 4.0: Smart Manufacturing and Advanced Robotics2021
Overview of predictive maintenance based on digital twin technology2023