Authors : Kavitha Subramaniam

Volume/Issue : Volume 11 - 2026, Issue 3 - March

Google Scholar : https://tinyurl.com/23s32mzt

Scribd : https://tinyurl.com/axt66p4z

DOI : https://doi.org/10.38124/ijisrt/26mar1106

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Reliable and secure autonomous Enterprise Resource Planning (ERP) systems are becoming more important as companies embrace intelligent automation to support complex, large scale and mission-critical business processes. The autonomous ERP system is likely to ease decision-making in the areas of finance, the supply chain, human resources, and compliance with limited human input. Here, the importance of safety, transparency, and accountability cannot be overstated because erroneous or unaccountable decisions may cause financial losses, compliance with the regulations, and lack of trust in the organization. Even though new advances in the field of artificial intelligence-driven ERP systems have been made recently, the current methods have multiple drawbacks. Vendor-specific architectures lead to low interoperability and longterm dependency whereas standard machine learning and deep learning models offer less autonomy and contextual reasoning. To address these issues, this paper will implement a new vendor-neutral system of safe and reliable autonomous ERP systems, called Retrieval-Augmented Generation (RAG). The new strategy combines knowledge semantic retrieval, generative reasoning in a context-sensitive manner, and validation-based execution. The structure uses proven enterprise knowledge, past records, and policy limitations to ground generative outputs, explainable and auditable autonomous decision-making and removes vendor lock-in. The outstanding innovation is that the retrieval is considered a safety and governance mechanism, not an improvement to the generative performance. Thorough experimental assessment proves that the proposed RAG-based ERP framework is uniformly more effective than rule-based, machine learning-oriented, and deep learning-based and generic generative ERP models in terms of accuracy, precision, recall, F1-score, and trustworthiness measures. The findings confirm the usefulness of the suggested framework in providing credible, clear, and business-ready autonomous ERP intelligence.

Keywords : Autonomous ERP Systems, Trustworthy Artificial Intelligence, Generative AI, Intelligent Enterprise Decision-Making, Retrieval-Augmented Generation (RAG) and Vendor-Neutral Architecture.

References :

1. M. S. Islam, M. I. Islam, A. Q. Mozumder, M. T. H. Khan, N. Das, and N. Mohammad, "A Conceptual Framework for Sustainable AI-ERP Integration in Dark Factories: Synthesising TOE, TAM, and IS Success Models for Autonomous Industrial Environments," Sustainability (2071-1050), vol. 17, 2025.
2. E. P. Nittala, "AI-Powered ERP Process Mining and Optimization Techniques for Agile Enterprise Transformation," American International Journal of Computer Science and Technology, vol. 7, pp. 15-24, 2025.
3. S. Sarferaz, "Implementing AI into ERP Software," Communications of the Association for Information Systems, vol. 57, p. 74, 2025.
4. V. Sridharan, "Ethical AI Integration in Enterprise Resource Planning Systems: A Framework for Balancing Innovation and Responsibility in B2B Environments," Journal of Computer Science and Technology Studies, vol. 7, pp. 489-504, 2025.
5. E. Niederwieser, D. Siegele, and D. T. Matt, "AI-Driven ERP Systems: Integrating Large Language Models for Enhanced Customer Interaction and Operational Efficiency," Zeitschrift für wirtschaftlichen Fabrikbetrieb, vol. 120, pp. 112-117, 2025.
6. M. M. Hasan, "A Framework-Based Meta-Analysis Of Artificial Intelligence-Driven ERP Solutions For Circular And Sustainable Supply Chains," International Journal of Scientific Interdisciplinary Research, vol. 6, pp. 327-367, 2025.
7. F. M. Ozman, "Systematic literature review on the rise of agentic AI in enterprise operations," International Journal of Frontiers in Science and Technology Research, vol. 8, pp. 001-015, 2025.
8. S. K. Vishwakarma, "AI-Driven Predictive Risk Modelling for Aerospace Supply Chains," International Interdisciplinary Business Economics Advancement Journal, vol. 6, pp. 102-134, 2025.
9. S. Amgothu, S. P. M. Gowda, and N. N. Sapavath, "AI-Driven Architectures for Real-Time Decision-Making in Autonomous Vehicles," in 2025 IEEE International Conference on AI and Data Analytics (ICAD), 2025, pp. 1-8.
10. K. Anjaria, "Enhancing organizational resilience and agility in S-ERP for industry 4.0," in Sustainable Enterprise Resource Planning (S-ERP) for Industry 4.0: A Secure and Ethical Deployment Approach, ed: Springer, 2025, pp. 277-301.
11. V. Ragu and P. J. Jayarin, "Detecting flooding attacks in distributed denial of service using deep neural network compared with decision tree," in AIP Conference Proceedings, 2025, p. 020229.
12. P. R. Nangi and C. K. R. N. Obannagari, "AI-Driven Security Automation for Continuous Compliance Monitoring in Regulated Cloud Environments," International Journal of Emerging Trends in Computer Science and Information Technology, vol. 6, pp. 95-105, 2025.
13. P. Ankireddy, S. Gopalakrishnan, and V. L. Reddy, "Gradient-enhanced focal-pooling vision transformer with adaptive tuning for robust and accurate vehicle detection in smart environments," Iran Journal of Computer Science, pp. 1-18, 2025.
14. S. Pitta, S. Gopalakrishnan, and S. R. Chand, "Securing WSN-IoT Networks using SwinAlert-GAN: A Deep Learning-based Intrusion Detection Framework," in 2025 Third International Conference on Augmented Intelligence and Sustainable Systems (ICAISS), 2025, pp. 211-218.