Hybrid Agentic AI and Multi-Agent Systems in Smart Manufacturing

2025-11-22

AI Summary

Traditional multi-agent systems (MAS) suffer from weak distributed coordination, insufficient autonomy, and limited higher-order reasoning and tool-integration capabilities—hindering their effectiveness in intelligent manufacturing, particularly for preventive maintenance. Method: This paper proposes a hierarchical hybrid autonomous agent framework tailored to preventive maintenance, leveraging large language models (LLMs) as strategic orchestrators, coordinated with lightweight rule-based agents and small language models (SLMs) at the edge to close the perception–analysis–decision–execution loop. The framework integrates feature analytics, dynamic model selection and optimization, human-in-the-loop (HITL) validation, and explainability mechanisms. Results: Evaluated on two industrial datasets, the system autonomously identifies data patterns, adaptively reconstructs preprocessing pipelines, optimizes model performance, and generates actionable, priority-ranked maintenance recommendations—demonstrating significant improvements in decision intelligence and engineering deployability.

Technology Category

• Multiagent Systems: Multiagent Learning
• Intelligent Robots: Multi-Robot Systems
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The convergence of Agentic AI and MAS enables a new paradigm for intelligent decision making in SMS. Traditional MAS architectures emphasize distributed coordination and specialized autonomy, while recent advances in agentic AI driven by LLMs introduce higher order reasoning, planning, and tool orchestration capabilities. This paper presents a hybrid agentic AI and multi agent framework for a Prescriptive Maintenance use case, where LLM based agents provide strategic orchestration and adaptive reasoning, complemented by rule based and SLMs agents performing efficient, domain specific tasks on the edge. The proposed framework adopts a layered architecture that consists of perception, preprocessing, analytics, and optimization layers, coordinated through an LLM Planner Agent that manages workflow decisions and context retention. Specialized agents autonomously handle schema discovery, intelligent feature analysis, model selection, and prescriptive optimization, while a HITL interface ensures transparency and auditability of generated maintenance recommendations. This hybrid design supports dynamic model adaptation, cost efficient maintenance scheduling, and interpretable decision making. An initial proof of concept implementation is validated on two industrial manufacturing datasets. The developed framework is modular and extensible, supporting seamless integration of new agents or domain modules as capabilities evolve. The results demonstrate the system capability to automatically detect schema, adapt preprocessing pipelines, optimize model performance through adaptive intelligence, and generate actionable, prioritized maintenance recommendations. The framework shows promise in achieving improved robustness, scalability, and explainability for RxM in smart manufacturing, bridging the gap between high level agentic reasoning and low level autonomous execution.

Problem

• Developing hybrid AI framework for intelligent decision-making in smart manufacturing
• Integrating agentic AI reasoning with multi-agent systems for prescriptive maintenance
• Bridging high-level strategic planning with low-level autonomous task execution

Innovation

• Hybrid agentic AI framework with layered architecture
• LLM Planner Agent coordinates workflow and context
• Specialized agents handle schema discovery and optimization