AI Agents and Agentic AI-Navigating a Plethora of Concepts for Future Manufacturing

2025-07-02

AI Summary

Ambiguity in definitions, ill-defined capability boundaries, and unclear application pathways hinder the adoption of AI agents—specifically LLM-based agents, multimodal large language model (MLLM) agents, and agentic AI—in intelligent manufacturing. Method: This study systematically traces their technological evolution, clarifies functional distinctions and synergies across perception–reasoning–decision-making dimensions, and proposes an integrated agent framework tailored for dynamic manufacturing environments. The framework unifies generative AI, large language models (LLMs), and MLLMs to enhance semantic understanding and autonomous decision-making. Contribution/Results: We establish, for the first time, a three-tiered AI agent architecture spanning technical, system, and application layers; identify critical challenges—including real-time adaptability, cross-modal alignment, and human–agent collaboration—and propose actionable, implementation-ready development pathways. The work provides both theoretical foundations and practical guidance for adaptive coordination and paradigmatic advancement in smart factories.

Technology Category

• Multiagent Systems: Agent/AI Theories and Architectures
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Intelligent Robots: Embodied AI

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

AI agents are autonomous systems designed to perceive, reason, and act within dynamic environments. With the rapid advancements in generative AI (GenAI), large language models (LLMs) and multimodal large language models (MLLMs) have significantly improved AI agents' capabilities in semantic comprehension, complex reasoning, and autonomous decision-making. At the same time, the rise of Agentic AI highlights adaptability and goal-directed autonomy in dynamic and complex environments. LLMs-based AI Agents (LLM-Agents), MLLMs-based AI Agents (MLLM-Agents), and Agentic AI contribute to expanding AI's capabilities in information processing, environmental perception, and autonomous decision-making, opening new avenues for smart manufacturing. However, the definitions, capability boundaries, and practical applications of these emerging AI paradigms in smart manufacturing remain unclear. To address this gap, this study systematically reviews the evolution of AI and AI agent technologies, examines the core concepts and technological advancements of LLM-Agents, MLLM-Agents, and Agentic AI, and explores their potential applications in and integration into manufacturing, along with the potential challenges they may face.

Problem

• Define AI agent capabilities in smart manufacturing
• Clarify boundaries of LLM and MLLM-based agents
• Explore integration challenges for Agentic AI in manufacturing

Innovation

• Utilizes generative AI for semantic comprehension
• Employs large language models for autonomous decisions
• Integrates Agentic AI for dynamic adaptability