Agentic AI for decentralized, natural-language communication and interaction between agents in self-organizing manufacturing systems

This is the authors' abstract. We don't add key points for this paper.

Self-organization in manufacturing systems has been a topic of research for several decades. Due to their inherent advantages, such as increased flexibility, robustness, and adaptability to dynamic environments, self-organizing systems are considered highly relevant for addressing modern manufacturing challenges. Still, only few industrial implementations of self-organization in manufacturing systems have been achieved so far. With recent advances in AI technologies, this paper investigates the potential of agentic AI to enable self-organizing, decentralized, and agent-based manufacturing systems. Specifically, a use case of an agentic AI-driven multi-agent system for manufacturing systems utilizing the tool calling and natural language processing capabilities of large language models is presented and validated. It demonstrates that large language model-based agents can facilitate dynamic task allocation through communication in natural language, thereby increasing the autonomy of single agents and advancing the practical realization of self-organization in manufacturing systems. The main challenge remaining is utilizing emergent behavior, as the current system was too limited in size to display it.