Adaptive task planning and coordination in multi-agent manufacturing systems using large language models

As the demand for personalized products increases, manufacturing processes are becoming more complex due to greater variety and uncertainty in product requirements. Traditional manufacturing systems face challenges in adapting to product changes without manual interventions, leading to an increase in product delays and operational costs. Multi-agent manufacturing control systems, a decentralized framework consisting of collaborative agents, have been employed to enhance flexibility and adaptability in manufacturing. However, existing multi-agent system approaches are often initialized with predefined capabilities, limiting their ability to handle new requirements that were not modeled in advance. To address this challenge, this work proposes a large language model-enabled multi-agent framework that enables adaptive matching, translating new product requirements to manufacturing process control at runtime. A product agent, which is a decision-maker for a product, interprets unforeseen product requirements and matches with manufacturing capabilities by dynamically retrieving manufacturing knowledge during runtime. Communication strategies and a decision-making method are also introduced to facilitate adaptive task planning and coordination. The proposed framework was evaluated using an assembly task board testbed across three case studies of increasing complexity. Results demonstrate that the framework can process unforeseen product requirements into executable operations, dynamically discover manufacturing capabilities, and improve resource utilization.