Intelligent Inventory Management in Behpakhsh Company's Supply Chain Using InvAgent: A Large Language Model Based on a Multi-Agent System
Downloads
Abstract
Behpakhsh Company, as one of the largest distribution and logistics companies in the country, plays a significant role in Supply Chain Management (SCM). SCM involves coordinating and integrating material, information, and financial flows across units to ensure the efficient and effective procurement and distribution of goods. In today's Volatile, Uncertain, Complex, and Ambiguous (VUCA) environment, effective inventory management is essential for the operational success of distribution companies. This paper examines the innovative approach adopted by Behpakhsh Company to leverage InvAgent technology, an artificial intelligence–based language model that uses zero-shot learning to enhance inventory management and reduce costs. By analyzing data and making intelligent decisions under changing conditions, InvAgent improves transparency and adaptability across Behpakhsh's supply chain. The implementation of this model has not only increased efficiency and productivity in Behpakhsh's distribution operations but also helped mitigate the risks of inventory shortages and excessive stockpiling. Ultimately, this study demonstrates that Behpakhsh, through advanced technologies and Large Language Models (LLMs), has achieved improved supply chain performance and enhanced customer satisfaction.
Keywords
Behpakhsh supply chain management Inventory management Large language model Zero-shot learning InvAgentReferences (13)
- [1] Quan, Y., Pothen, A., & Montreuil, B. (2023). Predictive demand disruption signals for supply chain networks. IISE annual conference and expo. IISE. https://www.researchgate.net/
- [2] Abaku, E. A., Edunjobi, T. E., & Odimarha, A. C. (2024). Theoretical approaches to AI in supply chain optimization: Pathways to efficiency and resilience. International journal of science and technology research archive, 6(1), 92–107. https://doi.org/10.53771/ijstra.2024.6.1.0033
- [3] Yasmin, G. (2024). Supply chain management: ensuring seamless operations. Journal of management science research review, 2(1), 55–66. https://www.jmsrr.com/index.php/Journal/article/view/25
- [4] Oroojlooyjadid, A., Nazari, M., Snyder, L. V, & Takáč, M. (2022). A deep q-network for the beer game: Deep reinforcement learning for inventory optimization. Manufacturing & service operations management, 24(1), 285–304. https://doi.org/10.1287/msom.2020.0939
- [5] Goodwin, J. S., & Franklin, S. G. (1994). The beer distribution game: using simulation to teach systems thinking. Journal of management development, 13(8), 7–15. https://doi.org/10.1108/02621719410071937
- [6] Edali, M., & Yasarcan, H. (2014). A mathematical model of the beer game. Journal of artificial societies and social simulation, 17(4), 2. https://doi.org/10.18564/jasss.2555
- [7] Mousa, M., van de Berg, D., Kotecha, N., del Rio Chanona, E. A., & Mowbray, M. (2024). An analysis of multi-agent reinforcement learning for decentralized inventory control systems. Computers & chemical engineering, 188, 108783. https://doi.org/10.1016/j.compchemeng.2024.108783
- [8] Kegenbekov, Z., & Jackson, I. (2021). Adaptive supply chain: Demand--supply synchronization using deep reinforcement learning. Algorithms, 14(8), 240. https://doi.org/10.3390/a14080240
- [9] Hubbs, C. D., Perez, H. D., Sarwar, O., Sahinidis, N. V, Grossmann, I. E., & Wassick, J. M. (2020). Or-gym: A reinforcement learning library for operations research problems. ArXiv preprint arxiv:2008.06319. https://doi.org/10.48550/arXiv.2008.06319
- [10] Wu, Q., Bansal, G., Zhang, J., Wu, Y., Li, B., Zhu, E., ... & Wang, C. (2024). Autogen: Enabling next-gen LLM applications via multi-agent conversations. First conference on language modeling. 1-46. https://openreview.net/pdf?id=BAakY1hNKS
- [11] Towers, M., Terry, J. K., Kwiatkowski, A., Balis, J. U., de Cola, G., Deleu, T., Goulão, M., Kallinteris, A., KG, A., Krimmel, M., Perez-Vicente, R., Pierré, A., Schulhoff, S., Tai, J. J., Shen, A. T. J., & Younis, O. G. (2023). Gymnasium. Zenodo. https://doi.org/10.5281/zenodo.8127025
- [12] Liang, E., Liaw, R., Nishihara, R., Moritz, P., Fox, R., Goldberg, K., ... & Stoica, I. (2018). RLlib: Abstractions for distributed reinforcement learning. In International conference on machine learning (pp. 3053-3062). PMLR. https://doi.org/10.48550/arXiv.1712.09381
- [13] Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., ... & McGrew, B. (2023). Gpt-4 technical report. arXiv preprint arXiv:2303.08774. https://doi.org/10.48550/arXiv.2303.08774
Article Metrics
- Published 2025-09-26
- Issue Vol. 2 No. 3 (2025): Supply Chain and Operations Decision Making
- Section Articles
- Document Type Research Article
- Views 1202
- Downloads 216
License
Copyright (c) 2025 Supply Chain and Operations Decision Making
This work is licensed under a Creative Commons Attribution 4.0 International License.