Modern manufacturing environments generate large volumes of operational exceptions involving production disruptions, material shortages, quality deviations, foreign-object detection, equipment anomalies, and process interruptions. Enterprise resource planning systems such as SAP S/4HANA Manufacturing provide structured transactional information for production planning and execution, but conventional exception management frequently remains dependent on human monitoring, rule-based alerts, and sequential investigation. This paper proposes a Multi-Agent Generative AI Framework for Autonomous Exception Management in SAP S/4HANA Manufacturing that integrates specialized intelligent agents for exception detection, contextual diagnosis, impact assessment, decision generation, and controlled resolution. The conceptual foundation is derived from the provided literature on machine-vision-based foreign-object detection, anomaly detection, three-dimensional perception, fault early warning, and industrial defect analysis. These studies demonstrate the value of automated perception and intelligent anomaly identification across heterogeneous manufacturing environments. Building upon these principles, the proposed framework organizes manufacturing exceptions into an agent-based decision pipeline connected to SAP production and material processes. The framework emphasizes autonomous reasoning while maintaining transactional controls through confidence thresholds, approval gates, and exception escalation. The resulting model indicates that multi-agent coordination can transform isolated anomaly signals into contextualized manufacturing decisions, thereby reducing response latency and improving operational resilience. However, limitations remain concerning data quality, explainability, integration complexity, model hallucination, and authorization of autonomous actions. The study contributes a research-oriented architecture for integrating generative AI agents with enterprise manufacturing exception management.
Multi-Agent Generative AI Framework for Autonomous Exception Management in SAP S/4HANA Manufacturing
DOI:
Abstract
References
Chao M, Kai C, Zhang Z. Research on tobacco foreign body detection device based on machine vision. Trans Inst Meas Control 2020; 42(15):2857–2871.
Chen S, Jang J, Chang Y, et al. An automatic foreign matter detection and sorting system for PVC Powder. Appl Sci 2022;12(12):6276.
Ho M, Obbard E, Burr P A, et al. A review on the development of nuclear power reactors. Energy Procedia 2019;160:459–466.
Hou J, Ma B, Liang L, et al. An early warning method for mechanical fault detection based on adversarial auto-encoders. J Adv Manuf Sci Technol 2022;2(2):2022006.
Ishii A, Mizuta T, Todo S. Detection of foreign substances mixed in a plastic bottle of medicinal solution using real-time video image processing. In: 14th International Conference on Pattern Recognition. 1998. p.1646–1650.
Lazarek J, Pryczek M. A review on point cloud semantic segmentation methods. J Appl Comput Sci 2018; 1507–0360.
Pan Y, Kong X, Yuan Y, et al. Detecting the foreign matter defect in lithium-ion batteries based on battery pilot manufacturing line data analyses. Energy 2023;262:125502.
Tan J, Zhang Z, Zheng H, et al. Corrosion fatigue model of austenitic stainless steels used in pressurized water reactor nuclear power plants. J Nucl Mater 2020;541:152407.
Wang D, Cao H. A comprehensive review on crack modeling and detection methods of aero-engine disks. J Adv Manuf Sci Technol 2022;2(3):2022012.
Xu L, Song Y, Zhang W, et al. An efficient foreign objects detection network for power substation. Image Vis Comput 2021;109:104159.
Xu X, Zhang L, Yang J, et al. Object detection based on fusion of sparse point cloud and image information. IEEE Trans Instrum Meas 2021;70:1–2.
Zhang K, Wang W, Lv Z, et al. Computer vision detection of foreign objects in coal processing using attention CNN. Eng Appl Artif Intell 2021;102:104242.
Zhang P, Zhong K, Li Z, J et al. High dynamic range 3D measurement based on structured light: A review. J Adv Manuf Sci Technol 2021;1(2):2021004.
Zhang Y, Yan Z, Zhu J, et al. A review of foreign object detection (FOD) for inductive power transfer systems. eTransportation 2019;1:100002.
M. Kalal, "Predictive Production Planning in Advanced Manufacturing Using SAP PP and Analytics," 2026 5th International Conference on Sentiment Analysis and Deep Learning (ICSADL), Birendranagar, Nepal, 2026, pp. 1363-1370, doi: 10.1109/ICSADL67539.2026.11452022.