Coordinating Supply Chain Agents Under Shared Inventory and Capacity Constraints
DOI:
https://doi.org/10.64137/31080030/IJFEMS-V2I3P113Keywords:
Multi-Agent Systems, Supply Chain Coordination, Shared Inventory, Capacity Constraints, Resource Allocation, Information Sharing, Bullwhip Effect, Inventory Management, M5 DatasetAbstract
Software agents acting for stores, a Distribution Centre (DC) and a plant share resources, and when their orders exceed supply, the rule that resolves the conflict shapes cost and service. This paper formulates coordination under four shared resources, namely DC stock, outbound transport, DC storage space and production capacity and proposes a coordination layer that aggregates agent state, detects conflicts, allocates scarce resources to equalise projected stock-out risk, and checks planned production against storage space. The layer is evaluated in a three-stage simulation driven by the real daily sales of 50 products per sample in ten Walmart stores (M5 data), over 20 samples, tuned on 2014 and tested on 536 later days. Proportional rationing cost 18.6% less than serving agents first come, first served. Echelon ordering on shared sales data cost 8.6% more, mainly because stock stranded at one store could not serve another. With stores merged, it cost 4.4% less. The coordination layer matched proportional rationing when capacity was slack and cost 4.7% to 11.9% less when production or transport ran at 95% to 98% utilisation, and it kept the fill rate 1.7 points higher during a production disruption. Balanced allocation drove most of these gains. The storage check helped only when transport was the bottleneck and raised cost when storage was tight, so balanced allocation without it was the best configuration in all other scenarios. Conflict-aware allocation pays off where resources run near their limits, and hard constraint checks must weigh the cost of what they prevent.
References
[1] O. Kwon, G. P. Im and K. C. Lee, “MACE-SCM: A multi-agent and case-based reasoning collaboration mechanism for supply chain management under supply and demand uncertainties,” Expert Systems with Applications, vol. 33, no. 3, pp. 690–705, Oct. 2007, doi: 10.1016/j.eswa.2006.06.015
[2] A. Surana, S. Kumara, M. Greaves, and U. N. Raghavan, “Supply-chain networks: a complex adaptive systems perspective,” International Journal of Production Research, vol. 43, no. 20, pp. 4235–4265, Oct. 2005, doi: 10.1080/00207540500142274
[3] H. L. Lee, V. Padmanabhan, and S. Whang, “Information Distortion in a Supply Chain: The Bullwhip Effect,” Management Science, vol. 50, no. 12_supplement, pp. 1875–1886, Dec. 2004, doi: 10.1287/mnsc.1040.0266
[4] J. D. Sterman, “Modeling Managerial Behavior: Misperceptions of Feedback in a Dynamic Decision Making Experiment,” Management Science, vol. 35, no. 3, pp. 321–339, Mar. 1989, doi: 10.1287/mnsc.35.3.321
[5] F. Chen, Z. Drezner, J. K. Ryan, and D. Simchi-Levi, “Quantifying the Bullwhip Effect in a Simple Supply Chain: The Impact of Forecasting, Lead Times, and Information,” Management Science, vol. 46, no. 3, pp. 436–443, Mar. 2000, doi: 10.1287/mnsc.46.3.436.12069
[6] G. P. Cachon and M. Fisher, “Supply Chain Inventory Management and the Value of Shared Information,” Management Science, vol. 46, no. 8, pp. 1032–1048, Aug. 2000, doi: 10.1287/mnsc.46.8.1032.12029
[7] A. J. Clark and H. Scarf, “Optimal Policies for a Multi-Echelon Inventory Problem,” Management Science, vol. 6, no. 4, pp. 475–490, July 1960, doi: 10.1287/mnsc.6.4.475
[8] Sven Axsater, Inventory Control. Springer International Pu, 2015.
[9] Gary Eppen and Linus Schrage, "Centralized ordering policies in a multi-warehouse system with lead times and random demand," Multi-Level Production/Inventory Control Systems: Theory and Practice, L. B. Schwarz, Ed., TIMS Studies in the Management Sciences, vol. 16. Amsterdam, The Netherlands: North-Holland, pp. 51–67, 1981.
[10] M. C. van der Heijden, E. B. Diks and A. G. de Kok, “Stock allocation in general multi-echelon distribution systems with (R, S) order-up-to-policies,” International Journal of Production Economics, vol. 49, no. 2, pp. 157–174, Apr. 1997, doi: 10.1016/s0925-5273(97)00005-4.
[11] G. P. Cachon and M. A. Lariviere, “Capacity Choice and Allocation: Strategic Behavior and Supply Chain Performance,” Management Science, vol. 45, no. 8, pp. 1091–1108, Aug. 1999, doi: 10.1287/mnsc.45.8.1091.
[12] G. P. Cachon and M. A. Lariviere, “An equilibrium analysis of linear, proportional and uniform allocation of scarce capacity,” IIE Transactions, vol. 31, no. 9, pp. 835–849, Sept. 1999, doi: 10.1080/07408179908969885
[13] J. M. Swaminathan, S. F. Smith, and N. M. Sadeh, “Modeling Supply Chain Dynamics: A Multiagent Approach,” Decision Sciences, vol. 29, no. 3, pp. 607–632, July 1998, doi: 10.1111/j.1540-5915.1998.tb01356.x
[14] M. S. Fox, M. Barbuceanu and R. Teigen, "Agent-oriented supply-chain management," International Journal of Flexible Manufacturing Systems, vol. 12, no. 2/3, pp. 165–188, 2000, doi: 10.1023/a:1008195614074
[15] R. G. Smith, “The Contract Net Protocol: High-Level Communication and Control in a Distributed Problem Solver,” IEEE Transactions on Computers, vol. C-29, no. 12, pp. 1104–1113, Dec. 1980, doi: 10.1109/tc.1980.1675516
[16] X. Liming, S. Mak, M. Minaricova, and A. Brintrup, “On implementing autonomous supply chains: A multi-agent system approach,” Computers in Industry, vol. 161, p. 104120, Oct. 2024, doi: 10.1016/j.compind.2024.104120.
[17] B. Rolf, I. Jackson, M. Müller, S. Lang, T. Reggelin, and D. Ivanov, “A review on reinforcement learning algorithms and applications in supply chain management,” International Journal of Production Research, vol. 61, no. 20, pp. 1–29, Nov. 2022, doi: 10.1080/00207543.2022.2140221
[18] A. Oroojlooyjadid, M. Nazari, L. V. Snyder, and M. Takáč, “A Deep Q-Network for the Beer Game: Deep Reinforcement Learning for Inventory Optimization,” Manufacturing & Service Operations Management, Feb. 2021, doi: 10.1287/msom.2020.0939.
[19] Y. Yang, M. Wang, J. Wang, P. Li, and M. Zhou, “Multi-Agent Deep Reinforcement Learning for Integrated Demand Forecasting and Inventory Optimization in Sensor-Enabled Retail Supply Chains,” Sensors, vol. 25, no. 8, p. 2428, Apr. 2025, doi: 10.3390/s25082428.
[20] B. Li, Konstantina Mellou, B. Zhang, Jeevan Pathuri, and Ishai Menache, “Large Language Models for Supply Chain Optimization,” arXiv (Cornell University), July 2023, doi: 10.48550/arxiv.2307.03875
[21] Y. Quan and Z. Liu, “InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains,” arXiv (Cornell University), July 2024, doi: 10.48550/arxiv.2407.11384.
[22] X. Zhao, Y. Xie, C. Chen and Y. Sun, "AIM-Bench: Evaluating decision-making biases of agentic LLM as inventory manager," arXiv:2508.11416, 2025.
[23] S. Makridakis, E. Spiliotis, and V. Assimakopoulos, “M5 accuracy competition: Results, findings, and conclusions,” International Journal of Forecasting, vol. 38, no. 4, Jan. 2022, doi: 10.1016/j.ijforecast.2021.11.013.
[24] K. Lee, W. Kim, and M. Kim, “Supply Chain Management using Multi-agent System,” Lecture Notes in Computer Science, pp. 215–225, 2004, doi: 10.1007/978-3-540-30104-2_16
[25] Y. Fu, Rajesh Piplani, D. de, and J.-R. Wu, “Multi-agent enabled modeling and simulation towards collaborative inventory management in supply chains,” Winter Simulation Conference, Dec. 2000, doi: 10.1109/wsc.2000.899167
[26] J. Du, V. Sugumaran, and B. Gao, “RFID and Multi-Agent Based Architecture for Information Sharing in Prefabricated Component Supply Chain,” IEEE Access, vol. 5, pp. 4132–4139, 2017, doi: 10.1109/access.2017.2665778
[27] M. Giannakis and M. Louis, “A multi-agent based system with big data processing for enhanced supply chain agility,” Journal of Enterprise Information Management, vol. 29, no. 5, pp. 706–727, Sept. 2016, doi: 10.1108/jeim-06-2015-0050
[28] David Pardoe and Peter Stone, "An autonomous agent for supply chain management," in Business Computing, G. Adomavicius and A. Gupta, Eds., Handbooks in Information Systems, Emerald Group Publishing, vol. 3, pp. 141–172, 2009.
[29] M. Herrera, M. Pérez-Hernández, A. Kumar Parlikad, and J. Izquierdo, “Multi-Agent Systems and Complex Networks: Review and Applications in Systems Engineering,” Processes, vol. 8, no. 3, p. 312, Mar. 2020, doi: 10.3390/pr8030312.
[30] X. Li and Q. Wang, “Coordination mechanisms of supply chain systems,” European Journal of Operational Research, vol. 179, no. 1, pp. 1–16, May 2007, doi: 10.1016/j.ejor.2006.06.023
[31] J. C. Hennet and Y. Arda, “Supply chain coordination: A game-theory approach,” Engineering Applications of Artificial Intelligence, vol. 21, no. 3, pp. 399–405, Apr. 2008, doi: 10.1016/j.engappai.2007.10.003.
[32] S. Gavirneni, R. Kapuscinski, and S. Tayur, “Value of Information in Capacitated Supply Chains,” Management Science, vol. 45, no. 1, pp. 16–24, Jan. 1999, doi: 10.1287/mnsc.45.1.16
[33] E. A. Silver, D. F. Pyke and D. J. Thomas, Inventory and Production Management in Supply Chains, 4th ed. Boca Raton, FL, USA: CRC Press, 2017.
[34] Ö. Özer, "Inventory management: Information, coordination, and rationality," in Planning Production and Inventories in the Extended Enterprise: A State of the Art Handbook, vol. 1, K. G. Kempf, P. Keskinocak and R. Uzsoy, Eds. New York, NY, USA: Springer, pp. 321–365, 2011.
[35] M. C. Gurbuz, Coordinated Replenishment Strategies in Multi-item Inventory/distribution Systems, 2007.
[36] G. Fliedner, “CPFR: an emerging supply chain tool,” Industrial Management & Data Systems, vol. 103, no. 1, pp. 14–21, Feb. 2003, doi: 10.1108/02635570310456850.
[37] J. A. Muckstadt, D. H. Murray, J. A. Rappold, and D. E. Collins, “Guidelines for Collaborative Supply Chain System Design and Operation,” Information Systems Frontiers, vol. 3, no. 4, pp. 427–453, 2001, doi: 10.1023/a:1012824820895
[38] S. C. Graves and S. P. Willems, “Optimizing Strategic Safety Stock Placement in Supply Chains,” Manufacturing & Service Operations Management, vol. 2, no. 1, pp. 68–83, Jan. 2000, doi: 10.1287/msom.2.1.68.23267
[39] L. S. Dias and M. G. Ierapetritou, “From process control to supply chain management: An overview of integrated decision making strategies,” Computers & Chemical Engineering, vol. 106, pp. 826–835, Nov. 2017, doi: 10.1016/j.compchemeng.2017.02.006.
[40] T. Rashid, Mikayel Samvelyan, C. Schroeder, G. Farquhar, J. Foerster, and Shimon Whiteson, “QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning,” Mar. 2018, doi: 10.48550/arxiv.1803.11485.
[41] R. Lowe, Y. Wu, A. Tamar, J. Harb, P. Abbeel and I. Mordatch, "Multi-agent actor-critic for mixed cooperative-competitive environments," NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 6382 - 6393, 2017.
[42] J. Foerster, G. Farquhar, T. Afouras, N. Nardelli and S. Whiteson, "Counterfactual multi-agent policy gradients," AAAI'18/IAAI'18/EAAI'18: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence, vol. 32, no. 1, pp. 2974 – 2982, Feb 2018.
[43] Z. Ji et al., “Survey of Hallucination in Natural Language Generation,” ACM Computing Surveys, vol. 55, no. 12, Nov. 2022, doi: 10.1145/3571730.
