Industrial Agentic AI: LLM-Driven New-Generation Agents for Smart Manufacturing

查看原文 / View Original 编辑 / Edit

Computer Science > Artificial Intelligence arXiv:2610.26941 (cs) [Submitted on 18 Oct 2026] Title:Industrial Agentic AI: LLM-Driven New-Generation Agents for Smart Manufacturing Authors:Lei Ren, Haiteng Wang, Shixiang Li, Jing Zhang, Yuqing Wang, Jingwei Guo, Yunfei Zhu, Yuanjun Laili, Yang Tang, Lihui Wang.

计算机科学 > 人工智能 arXiv:2610.26941 (cs) [提交于 2026 年 10 月 18 日] 标题：工业代理人工智能：用于智能制造的 LLM 驱动的新一代代理作者：Lei Ren, Haiteng Wang, Shixiang Li, Jing Zhang, Yuqing Wang, Jingwei Guo, Yunfei Zhu, Yuanjun Laili, Yang Tang, Lihui Wang。

Abstract: Large language models (LLMs) are enabling agents to move beyond predefined workflows toward autonomous planning and execution, creating new opportunities for smart manufacturing. However, dynamic environments, complex physical constraints, and stringent reliability requirements hinder the direct deployment of general-purpose agents in smart manufacturing.

摘要：大型语言模型 (LLM) 正在使代理能够超越预定义的工作流程，转向自主规划和执行，从而为智能制造创造了新的机遇。然而，动态环境、复杂的物理约束以及严格的可靠性要求阻碍了通用代理在智能制造中的直接部署。

This article presents a systematic overview of LLM-driven industrial agents. First, we analyze five key challenges and discuss the concept and core characteristics of industrial agents. We then establish a unified taxonomy covering application scenarios, embodiment forms, and five capability levels.

本文对 LLM 驱动的工业代理进行了系统概述。首先，我们分析了五个关键挑战，并讨论了工业代理的概念和核心特征。随后，我们建立了一个涵盖应用场景、具身形式和五个能力等级的统一分类法。

Next, we propose a four-layer system architecture and detail its core modules and operational mechanisms for closed-loop task execution. Finally, we review representative applications across the industrial lifecycle and outline future research directions. This article provides a structured reference for the design, development, and application of industrial agents.

接下来，我们提出了一个四层系统架构，并详细介绍了其用于闭环任务执行的核心模块和运行机制。最后，我们回顾了整个工业生命周期中的代表性应用，并概述了未来的研究方向。本文为工业代理的设计、开发和应用提供了结构化的参考。