Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open Challenges
Organizations: Institute of Automation Technology, Helmut Schmidt University / University of the Federal Armed Forces Hamburg, Hamburg, Germany. · Siemens AG, Nuremberg, Germany; Institute for Technologies and Management of Digital Transformation, Bergische Universität Wuppertal, Germany. · Artiquare GmbH, Ingolstadt, Germany. · Facultad de Ingenier´ıa Mec´anica, Electr´onica y Biom´edica (FIMEB), Universidad Antonio Nari˜no, Bogot´a, Colombia. · Chair of Information Systems and Supply Chain Management, University of Münster, Münster, Germany. · Fraunhofer Institute for Manufacturing Technology and Advanced Materials IFAM, Stade, Germany. · Research Group on Cognitive Autonomy & Predictive Intelligence, Faculty of Electrical Engineering, Technical University of Applied Sciences Augsburg, Augsburg, Germany. · Birkenfeld Institutes of Technology, Trier University of Applied Sciences, Birkenfeld, Germany. · Fraunhofer Institute for Manufacturing Engineering and Automation IPA, Stuttgart, Germany. · Honda Research Institute Europe, Offenbach am Main, Germany. · Faculty of Computer Science, Augsburg Technical University of Applied Sciences, Augsburg, Germany. · Institute for Automation and Communication (ifak), Magdeburg, Germany. · Process-to-Order Group, TUD Dresden University of Technology, Dresden, Germany. · Institute for Industrial Automation and Software Engineering, University of Stuttgart, Stuttgart, Germany.
Abstract
Foundation models, particularly large language models, are increasingly integrated into agent architectures for industrial tasks such as decision support, process monitoring, and engineering automation. Yet evidence on their purposes, capabilities, and limitations remains fragmented across domains. This work examines how mature foundation-model-based agent systems are in industrial contexts, how their functional profile differs from conventional agent systems, and which limitations persist. A systematic literature survey following the PRISMA 2020 guideline is presented, screening 2,341 publications and synthesising a corpus of 88 publications through a structured coding scheme. The results show that reported systems are predominantly at prototype and early validation stages (75.0% at TRL 4-6), with deployment-oriented evidence remaining rare (9.1%). Operational goals are most frequently positioned in user assistance, monitoring, and process optimisation, while conventional production-control purposes such as planning and scheduling are less prominent. Compared with an established baseline for industrial agent systems, the capability profile reveals substantial gains in human interaction (+37%) and dealing with uncertainty (+35%), but a pronounced deficit in negotiation (-39%). The most widely reported limitations concern lack of generalization, hallucination and output instability, data scarcity, and inference latency. A working definition of foundation-model-based industrial agents is also proposed, bridging conventional agent theory, automation-engineering standards, and the foundation-model paradigm.