Multi-Agent LLM Systems for Autonomous Supply Chain Disruption Analysis and Resilient Recovery Planning

References

[1] N. K. Jingar, “Automated Incident Intelligence In Supply Chains Using Agentic AI And Root Cause Reasoning,” Zenodo (CERN European Organization for Nuclear Research), Sep. 2023. https://doi.org/10.5281/zenodo.18628070

[2] L. Xu, S. AlMahri, S. Mak, and A. Brintrup, “Multi-Agent Systems and Foundation Models Enable Autonomous Supply Chains: Opportunities and Challenges,” IFAC-PapersOnLine, vol. 58, no. 19, pp. 795–800, Jan. 2024. Crossref

[3] L. Xu, S. Mak, and A. Brintrup, “Will bots take over the supply chain? Revisiting agent-based supply chain automation,” arXiv (Cornell University), vol. 241, p. 108279, Sep. 2021.

[4] S. AlMahri, L. Xu, and A. Brintrup, “Automating Supply Chain Disruption Monitoring via an Agentic AI Approach,” ArXiv.org, Jan. 2026, Accessed: Feb. 2026. [Online]. Available: http://arxiv.org/abs/2601.09680

[5] V. Jannelli, S. Schöpf, M. Bickel, T. H. Netland, and A. Brintrup, “Agentic LLMs in the supply chain: towards autonomous multi-agent consensus-seeking,” International Journal of Production Research, pp. 1–31, Dec. 2025. Crossref

[6] N. K. Jingar, “Ensuring Safety, Accountability, and Drift Resistance in LLM-Based Supply Chain Optimization,” International Journal of Scientific Research in Science Engineering and Technology, p. 472, Jan. 2023. Crossref

[7] Y. Duan, Y. Hu, and J. Jiang, “Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory Control,” Dec. 31, 2025, Cornell University. https://doi.org/10.48550/arxiv.2601.00121

[8] J. Baek, Y. Fu, W. Ma, and T. Peng, “AI Agents for Inventory Control: Human-LLM-OR Complementarity,” Feb. 13, 2026, Cornell University. https://doi.org/10.48550/arxiv.2602.12631

[9] S. K. Srivastava, S. Routray, S. Bag, S. Gupta, and Z. Zhang, “Exploring the Potential of Large Language Models in Supply Chain Management,” Journal of Global Information Management, vol. 32, no. 1, pp. 1–29, Jan. 2024. Crossref

[10] Nissen and Sengupta, “Incorporating Software Agents into Supply Chains: Experimental Investigation with a Procurement Task1,” MIS Quarterly, vol. 30, no. 1, pp. 145–166, Mar. 2006. Crossref

[11] S. N. Kirshner, Y. Pan, J. Wu, and A. N. Gould, “Talking terms: Agent information in LLM supply chain bargaining,” Decision Sciences, vol. 57, no. 1, pp. 9–23, Jul. 2025.

[12] M. Almutairi and H. Kim, “Resilient Multi-Agent Negotiation for Medical Supply Chains:Integrating LLMs and Blockchain for Transparent Coordination,” Jul. 23, 2025. https://doi.org/10.48550/arxiv.2507.17134

[13] J. Wang, “Multimodal Deep Learning Approach for Early Warning of Supply Chain Disruptions Using NLP and Anomaly Detection,” Artificial Intelligence and Machine Learning Review, vol. 5, no. 3, pp. 98–110, Jul. 2024. Crossref

[14] Sichong Huang, “AI-Driven Early Warning Systems for Supply Chain Risk Detection: A Machine Learning Approach,” Academic Journal of Computing & Information Science, vol. 8, no. 9, Jan. 2025. Crossref

[15] S. Guan, Y. Liu, and L. Cao, “SupChain-Bench: Benchmarking Large Language Models for Real-World Supply Chain Management,” arXiv (Cornell University), Feb. 2026, Accessed: Feb. 2026. [Online]. Available: http://arxiv.org/abs/2602.07342

[16] Y. Cui et al., “CSCBench: A PVC Diagnostic Benchmark for Commodity Supply Chain Reasoning,” Jan. 05, 2026, Cornell University. https://doi.org/10.48550/arxiv.2601.01825

[17] T. T. Yu et al., “SMARTAPS: Tool-augmented LLMs for Operations Management,” Jul. 23, 2025. https://doi.org/10.48550/arxiv.2507.17927

[18] K. Yoshizato, K. Shimizu, R. Higa, and T. Otsuka, “AI Agent Systems for Supply Chains: Structured Decision Prompts and Memory Retrieval,” Feb. 05, 2026, Cornell University. https://doi.org/10.48550/arxiv.2602.05524

[19] Y. Quan and Z. Liu, “InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains,” Jul. 16, 2024, Cornell University. https://doi.org/10.48550/arxiv.2407.11384

[20] A. Awad and D. Alahmari, “Agentic Control Towers,” in Advances in computational intelligence and robotics book series, IGI Global, 2025, pp. 161–182.

[21] Y. Wang and K. Li, “Large Language Models in Operations Research: Methods, Applications, and Challenges,” Sep. 18, 2025, Cornell University. https://doi.org/10.48550/arxiv.2509.18180

[22] G. Ghiani, E. Manni, and S. Zacchino, “Improving Adaptability in Optimization-Based Decision Support Systems Through Large Language Models,” IEEE Access, vol. 13, pp. 149777–149788, Jan. 2025. Crossref

[23] S. Wasserkrug et al., “Enhancing Decision Making Through the Integration of Large Language Models and Operations Research Optimization,” in Proceedings of the AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, Apr. 2025, pp. 28643–28650. Crossref

[24] J. Li, R. Wickman, S. Bhatnagar, R. K. Maity, and A. P. Mukherjee, “Abstract Operations Research Modeling Using Natural Language Inputs,” Information, vol. 16, no. 2, p. 128, Feb. 2025. Crossref

[25] Y. Yan et al., “Large Language Models for Traffic and Transportation Research: Methodologies, State of the Art, and Future Opportunities,” Mar. 27, 2025. https://doi.org/10.48550/arxiv.2503.21330

[26] R. Wu, “Inventory optimization under supply chain disruptions: Leveraging large language models for human-AI collaborative decision-making,” Journal of King Saud University - Computer and Information Sciences, vol. 38, no. 2, Jan. 2026. Crossref

[27] S. Venkatachalam, “Integrating Large Language Models with Network Optimization for Interactive and Explainable Supply Chain Planning: A Real-World Case Study,” Aug. 29, 2025. https://doi.org/10.48550/arxiv.2508.21622

[28] D. Ivanov and A. Dolgui, “Stress testing supply chains and creating viable ecosystems,” Operations Management Research, vol. 15, pp. 475–486, May 2021.

[29] C. Liu, Y. Wang, L. Purvis, and A. Potter, “Can Digital Twin Technology Enhance Supply-Chain Resilience? A Systematic Literature Review,” Sustainability, vol. 18, no. 5, p. 2361, Feb. 2026. Crossref

[30] A. Cimino, F. Longo, G. Mirabelli, and V. Solina, “A cyclic and holistic methodology to exploit the Supply Chain Digital Twin concept towards a more resilient and sustainable future,” Cleaner Logistics and Supply Chain, vol. 11, p. 100154, Apr. 2024. Crossref

[31] Davenport, “GUARDRAIL-CENTRIC FINE-TUNING FOR DETERMINISTIC DECISION SYSTEMS,” Zenodo (CERN European Organization for Nuclear Research), Jan. 2026. https://doi.org/10.5281/zenodo.18305825

[32] T. A. Syed, M. R. Belgaum, S. Jan, A. A. Khan, and S. S. Alqahtani, “Agentic AI for Autonomous Defense in Software Supply Chain Security: Beyond Provenance to Vulnerability Mitigation,” ArXiv.org, Dec. 2025, Accessed: Mar. 2026. [Online]. Available: http://arxiv.org/abs/2512.23480

[33] T. Maiti, “Application of Large Language Models (LLM’s) for Supply Chain Optimization,” INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT, vol. 9, no. 5, pp. 1–9, May 2025. Crossref

[34] P. Brandtner and F. Hofer, “Enhancing Procurement Processes in Supply Chain Management with Large Language Models,” Procedia Computer Science, vol. 278, pp. 308–315, Jan. 2026. Crossref

@article{1723011,
      author = {Sohail Sayed, Nauman Sayed},
      title = {Multi-Agent LLM Systems for Autonomous Supply Chain Disruption Analysis and Resilient Recovery Planning},
      journal = {Iconic Research And Engineering Journals},
      year = {2024},
      volume = {8},
      number = {6},
      pages = {1344-1357},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1723011.pdf},
      abstract = {Supply chain disruption management remains dominated by manual, reactive processes: analysts triage alerts, root causes are identified slowly, and recovery plans lag the events they are meant to counter [1]. This paper argues that multi-agent systems powered by large language models — generalist agents with multi-faceted decision-making that communicate in natural language — are the convergence point that enables autonomous disruption analysis and resilient recovery planning, two decades of agent-based supply chain research having been held back by implementation difficulty and black-box behavior [2], [3]. We propose ORCHESTRA-SC, a governed multi-agent framework coupling (i) specialized analysis agents (monitoring, causal root-cause reasoning, network-exposure assessment), (ii) a consensus-seeking negotiation layer in which agents representing facilities and functions reconcile selfish objectives with systemic outcomes, (iii) a recovery-planning layer that transpiles agent consensus into solver-verified plans through LLM–OR integration, (iv) a digital-twin simulation loop for stress-testing recovery strategies, and (v) guardrail, audit, and drift-resistance governance. The framework consolidates the reported evidence envelope: a seven-agent agentic framework detects, analyses, and responds to disruptions across extended networks with F1 scores between 0.962 and 0.991, completes end-to-end analyses in a mean of 3.83 minutes at $0.0836 per disruption — more than three orders of magnitude faster than multi-day analyst assessments, validated on the 2022 Russia–Ukraine conflict [4]; agentic root-cause reasoning reduces mean time to root-cause identification by 30% and improves incident-resolution accuracy by 22% while surfacing hidden dependencies missed by baselines [1]; consensus-seeking LLM agents reduce the bullwhip effect and, equipped with tools, minimize it better than restocking policies and centralized demand approaches [5]; a governed LLM optimization framework cuts unsafe decision outputs by 45% and sustains drift-detection accuracy above 92% [6]; a hybrid agentic inventory framework strictly decoupling semantic reasoning from mathematical calculation reduces total inventory costs by 32.1% relative to an interactive GPT-4o end-to-end solver [7]; and OR-augmented LLM agents outperform either approach in isolation, with human–AI teams achieving higher profits than humans or agents alone across more than 1,000 benchmark instances [8]. The paper argues that the autonomy ladder — from assisted analysis to governed action — is climbed one verified capability at a time, and that consensus, grounding, and digital-twin validation are what separate multi-agent experiments from multi-agent operations.},
      keywords = {Multi-agent systems, large language models, agentic AI, supply chain disruption, recovery planning, consensus-seeking, digital twin, reinforcement learning governance, supply chain resilience.},
      month = {December},
      doi = {https://doi.org/10.64388/IREV8I6-1723011}
  }