A Large Language Model-Enabled Control Architecture for Dynamic Resource Capability Exploration in Multi-Agent Manufacturing Systems

2025-05-28

AI Summary

To address frequent demand fluctuations, unpredictable disturbances, and delayed responses in dynamic manufacturing environments, this paper proposes a large language model (LLM)-enhanced multi-agent control architecture. The method integrates an LLM directly into the manufacturing control loop—enabling semantic task parsing, real-time resource capability perception, context-aware dynamic capability reasoning, and heterogeneous resource coordination. By synergizing multi-agent systems (MAS), event-driven simulation, and real-time resource modeling, it overcomes key limitations of conventional MAS in contextual understanding, adaptive exploration, and real-time responsiveness. Experimental results demonstrate a 19.3% increase in system throughput, a 22.7% improvement in resource utilization, and a 41% reduction in disturbance recovery time. Collectively, these advances significantly enhance the resilience and flexibility of manufacturing systems.

Technology Category

• Multiagent Systems: Multiagent Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Manufacturing environments are becoming more complex and unpredictable due to factors such as demand variations and shorter product lifespans. This complexity requires real-time decision-making and adaptation to disruptions. Traditional control approaches highlight the need for advanced control strategies capable of overcoming unforeseen challenges, as they demonstrate limitations in responsiveness within dynamic industrial settings. Multi-agent systems address these challenges through decentralization of decision-making, enabling systems to respond dynamically to operational changes. However, current multi-agent systems encounter challenges related to real-time adaptation, context-aware decision-making, and the dynamic exploration of resource capabilities. Large language models provide the possibility to overcome these limitations through context-aware decision-making capabilities. This paper introduces a large language model-enabled control architecture for multi-agent manufacturing systems to dynamically explore resource capabilities in response to real-time disruptions. A simulation-based case study demonstrates that the proposed architecture improves system resilience and flexibility. The case study findings show improved throughput and efficient resource utilization compared to existing approaches.

Problem

• Dynamic resource capability exploration in multi-agent manufacturing systems
• Real-time adaptation and context-aware decision-making challenges
• Enhancing system resilience and flexibility with LLM-enabled control

Innovation

• LLM-enabled control for dynamic resource exploration
• Multi-agent systems with real-time adaptation
• Context-aware decision-making in manufacturing