Authors : Pranita Pingale; Faiz Asif Shaikh; Om Sanjay Bhongale; Sanvesh Satish Patil

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

Google Scholar : https://tinyurl.com/39eus6xv

Scribd : https://tinyurl.com/mtr4h4y9

DOI : https://doi.org/10.38124/ijisrt/26mar1951

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

Abstract : Modern supply chain management systems often suffer from fragmented decision-making where demand forecasting, inventory control, supplier management, and pricing operate as independent processes. This lack of coordination frequently leads to inefficiencies such as stockouts, excess inventory, revenue loss, and poor supplier utilization. To address these challenges, this paper presents StockSage, a multi-agent inventory management system powered by Large Language Models (LLMs). The proposed system employs four specialized agents responsible for forecasting demand, managing inventory levels, selecting optimal suppliers, and recommending pricing strategies. These agents collaborate through a structured two-round coordination protocol that enables cross-functional communication and adaptive decisionmaking. The system is implemented as a full-stack web application using modern technologies including Next.js, React, TypeScript, Prisma ORM, SQLite, and OpenAI GPT APIs. A Monte Carlo simulation framework is used to evaluate system performance against traditional baseline strategies such as static reorder policies, moving average forecasting, and fixed pricing methods. Experimental results indicate improvements in forecast accuracy, service level, inventory turnover, and revenue optimization. The results demonstrate the potential of coordinated multi-agent LLM systems to provide intelligent, explainable, and scalable decision support for modern inventory and supply chain management.

Keywords : Multi-Agent Systems; Large Language Models; Inventory Management; Supply Chain Optimization; Demand Forecasting; Decision Explainability; Dynamic Pricing.

References :

1. Y. Wang, J. Liu, and H. Zhang, “InvAgent: a large language model based multi-agent system for inventory management in supply chains,” arXiv preprint, arXiv:2503.07231, 2025.
2. Z. Xu, L. Chen, and Q. Huang, “Large language models for UNSPSC item categorization in industrial supply chains,” arXiv preprint, arXiv:2407.11384, 2024.
3. X. Li, Y. Zhao, and P. Sun, “Large language models for industrial automation: event-driven decision systems,” arXiv preprint, 2025.
4. R. Huang, S. Wang, and T. Li, “Resource-efficient large language models for industrial applications: techniques and challenges,” arXiv preprint, 2025.
5. J. Gijsbrechts, R. Boute, and J. Van Mieghem, “Learning-based inventory control: a review of machine learning and reinforcement learning methods,” European Journal of Operational Research, 2024.
6. M. Sadeghi and Q. Zhao, “Deep reinforcement learning for vendor managed inventory in semiconductor supply chains,” in Proceedings of the Winter Simulation Conference, 2023.
7. Y. Xu, H. Li, and X. Chen, “Deep reinforcement learning for inventory control under random demand and lead times,” Computers & Industrial Engineering, 2024.
8. K. Zhang, L. Wang, and D. Li, “Deep reinforcement learning for dynamic pricing and ordering policies in perishable inventory management,” 2024.
9. S. Narayanan, R. Gupta, and A. Kumar, “Multi-echelon inventory optimization using deep reinforcement learning,” 2023.
10. J. Ahn, S. Lee, and D. Kim, “Federated graph neural networks for supply chain link prediction,” arXiv preprint, 2025.
11. R. Goyal, P. Sharma, and M. Gupta, “Graph learning in supply networks: a survey of graph neural network approaches,” arXiv preprint, 2025.
12. Y. Qiu, Z. Chen, and H. Wang, “Artificial intelligence driven green supply chain management and sustainability performance,” 2024.
13. F. Lin, Y. Chen, and T. Zhang, “Artificial intelligence and metaverse applications in supply chain management,” 2023.
14. S. Saghafian and M. Van Oyen, “Artificial intelligence in supply chain optimization: opportunities and challenges,” IEEE Transactions on Engineering Management, 2024.