This systematic review explores the intersection between Multi-Agent Systems and Digital Twins, with a particular focus on predictive maintenance applications in resource-constrained contexts and reveals that, despite significant progress, no existing system offers an integrated embedded-distributed hierarchical solution that simultaneously meets the requirements of Industry 5.0.
Abstract
Digital twins have emerged as a foundational technology within the context of Industry 4.0, offering a paradigm for the real-time virtual representation of physical systems. However, managing their growing complexity, particularly in distributed industrial environments, requires intelligent architectures capable of autonomous decision-making, dynamic adaptability, and inter-agent coordination. This systematic review explores the intersection between Multi-Agent Systems and Digital Twins, with a particular focus on predictive maintenance applications in resource-constrained contexts. Through a critical analysis of over 547 papers published in high-impact journals (IEEE Transactions, Nature, Elsevier, MDPI), we establish a taxonomy of existing hybrid architectures, identify persistent technological bottlenecks, and formulate three open research questions concerning: (i) the deployment of artificial intelligence on resource-constrained microcontrollers, (ii) distributed multi-node coordination via lightweight communication protocols, and (iii) the hierarchical orchestration of Digital Twins toward smart factory control integrating residual life estimation and explainable Artificial Intelligence. The results of this analysis reveal that, despite significant progress, no existing system offers an integrated embedded-distributed hierarchical solution that simultaneously meets the requirements of Industry 5.0.
The main conclusion is that practical Agentic IoT depends less on placing an entire agent at one tier than on partitioning perception, memory, reasoning, and action under explicit latency, privacy, reliability, and safety constraints.
A unified, taxonomy-driven, and deployment-oriented survey of agentic AI systems, synthesizing recent advances through a modular reference architecture and a four-dimensional taxonomy that characterizes agents along the axes of autonomy, tool use, collaboration, and safety–governance is presented.
Sparsh Bajoria, Shreyanshu Ranjan, Adhitya M et al.· Cognitive Computation· 0 citations
Through applied case studies in pharmaceutical discovery and financial systems, common design patterns that make agentic systems successful are analyzed, and practical mitigation strategies for failure modes are discussed, such as verification pipelines, fallback mechanisms, and human-in-the-loop supervision.
Grace Hui Yang, P. Venkit, Hooman Sedghamiz et al.· Proceedings of the 32nd ACM...· 0 citations
The findings indicate that scalability should be understood not merely as increasing computational capacity but as the ability to expand AI-enabled construction processes without proportionally increasing coordination complexity, training requirements, or operational risk.
Takumi Suzuki, Mio Tanaka· International Journal of Adv...· 0 citations
With the advent of Artificial Intelligence (AI), the world of enterprise automation has radically changed to an AI multi-agent ecosystem with coordination across functional teams and the capacity to make autonomous decisions. Despite this, many companies are still discontinuing the implementation of AI, with partial integration into their processes, weak systems integration, and a lack of a sense of network in some business units. It introduces the concept of the traditional enterprise transforming into an intelligent, autonomous enterprise with the help of AI in logistics, knowledge management, finances, HR, cybersecurity, compliance, customer support, and operational analytics, and also introduces the Multi-Agent Enterprise Framework (MAEF) as the scalable architecture. The proposed architecture has four layers: shared memory, human in the loop, policy-driven control, and orchestration layer, which are necessary for safe, transparent, and trustworthy cooperation between the set of specialized agents. Training is conducted in a highly realistic business environment that includes several departments, numerous workflow requests, and is evaluated and tested against standard automated and single-agent AI systems. Experimental results show that workflow automation and task completion time have been enhanced, cross-department collaboration has been effective, operational efficiency has been achieved, and resources are used optimally; meanwhile, the governance and compliance requirements are met. Agreeing with these conclusions, it seems that enterprise-wide multi-agent systems are a good building block for digital enterprises capable of adapting, scaling, and operating autonomously, on which future intelligent businesses would be able to operate.
Swaroop Suresh Borukar· International Research Journ...· 0 citations
The rapid evolution of Industry 5.0 has accelerated the integration of intelligent automation, artificial intelligence (AI), Industrial Internet of Things (IIoT), and cyber-physical systems into modern manufacturing environments. One of these newly developed technologies, DT technology has recently emerged as one of the transformational paradigms in realising predictive intelligence, autonomous maintenance and online operational optimisation of robotic systems. Conventional robotic maintenance strategies, such as corrective and preventive maintenance often lead to unexpected downtimes, unnecessary resources allocation and inflated maintenance costs largely due to the nature of scheduled inspections or post-failure interventions. The maintenance frameworks enabled by Digital Twin overcome these limitations as they deterministically establish a dynamically-updated virtual representation of physical robotic assets connecting sensor networks, cloud-edge computing, AI analytics and real-time simulation. This paper proposes a full Digital Twin-based autonomous robotic maintenance framework along with data acquisition from multiple sensors, edge intelligence, machine learning (ML)-based diagnosis and prediction of failures and autonomous decision-making for predictive maintenance. The proposed framework supports continuous monitoring of health, anomaly detection, RUL prediction and adaptive maintenance scheduling with minimal operational disruptions. A comparative analysis reveals that Digital Twin-assisted maintenance not only increases fault detection precision, maintenance efficiency, system availability, and operational reliability compared to traditional practices. It further discusses the current technological challenges, research gaps, and avenues for future work relating to federated Digital Twins, explainable AI (XAI), collaborative robotics, and sustainable intelligent maintenance systems. This framework lays a strong, scalable foundation for Industry 5.0 ecosystems of next generation autonomous robotic maintenance in the smart factory.
O. Olesen· International Journal of Int...· 0 citations