• Nirmal Kumar Jingar

Modern supply chains are highly complex, distributed, and dynamic, making real-time optimization difficult under uncertainty, disruptions, and scale. Traditional optimization systems struggle to adapt to rapidly changing demand, logistics constraints, and multi-stakeholder objectives while maintaining trust and explainability. Existing works mainly rely on rule-based systems, classical optimization, or isolated machine learning models. While these methods improve efficiency, they lack autonomous decision-making, cross-domain reasoning, and transparency. Most approaches also fail to ensure trustworthiness, as they provide limited interpretability and weak handling of unseen disruptions. This paper proposes an agentic and generative AI-based architecture for large-scale supply chain optimization. The system consists of collaborative AI agents responsible for demand forecasting, inventory planning, logistics coordination, and risk mitigation. Generative AI models enable scenario simulation, decision explanation, and adaptive strategy generation. A trust layer incorporating policy constraints, explainability modules, and feedback validation ensures reliable and accountable decisions. Experimental evaluation using large-scale synthetic and real-world supply chain datasets demonstrates significant improvements in cost reduction, service level, and disruption recovery time compared to traditional baselines. The proposed architecture achieves up to 18% improvement in operational efficiency and 25% faster response to disruptions, while providing human-interpretable decision rationales. These results show that agentic and generative AI can enable scalable, trustworthy, and resilient supply chain optimization.

Agentic AI; Generative Artificial Intelligence; Supply Chain Optimization; Autonomous Decision-Making; Trustworthy AI; Sustainable Supply Chain Management; Multi-Agent Systems; Large-Scale Optimization; Explainable AI; Decision Accuracy

"Agentic and Generative AI Architectures for Trustworthy, Large-Scale Supply Chain Optimization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 10, page no.g596-g606, October-2024, Available :http://www.jetir.org/papers/JETIR2410670.pdf

"Agentic and Generative AI Architectures for Trustworthy, Large-Scale Supply Chain Optimization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 10, page no. ppg596-g606, October-2024, Available at : http://www.jetir.org/papers/JETIR2410670.pdf