Automating Supply Chain Disruption Monitoring via an Agentic AI Approach

2026-01-14

AI Summary

This study addresses the widespread lack of visibility across multi-tier supply chains, which hinders enterprises from promptly responding to upstream disruptions. To tackle this challenge, the authors propose the first lightly supervised framework that integrates large language models with a multi-agent architecture, featuring seven specialized agents that collaboratively enable end-to-end disruption detection, risk assessment, and alternative sourcing recommendations. Evaluated on 30 synthetic scenarios, the method achieves F1 scores ranging from 0.962 to 0.991, completes each analysis in an average of 3.83 minutes at a cost of merely $0.0836 per run, and accelerates response times by over three orders of magnitude compared to manual approaches. Its practical efficacy is further validated through a real-world case study of the Russia–Ukraine conflict.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Distributed Problem Solving
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Modern supply chains are increasingly exposed to disruptions from geopolitical events, demand shocks, trade restrictions, to natural disasters. While many of these disruptions originate deep in the supply network, most companies still lack visibility beyond Tier-1 suppliers, leaving upstream vulnerabilities undetected until the impact cascades downstream. To overcome this blind-spot and move from reactive recovery to proactive resilience, we introduce a minimally supervised agentic AI framework that autonomously monitors, analyses, and responds to disruptions across extended supply networks. The architecture comprises seven specialised agents powered by large language models and deterministic tools that jointly detect disruption signals from unstructured news, map them to multi-tier supplier networks, evaluate exposure based on network structure, and recommend mitigations such as alternative sourcing options. \rev{We evaluate the framework across 30 synthesised scenarios covering three automotive manufacturers and five disruption classes. The system achieves high accuracy across core tasks, with F1 scores between 0.962 and 0.991, and performs full end-to-end analyses in a mean of 3.83 minutes at a cost of \$0.0836 per disruption. Relative to industry benchmarks of multi-day, analyst-driven assessments, this represents a reduction of more than three orders of magnitude in response time. A real-world case study of the 2022 Russia-Ukraine conflict further demonstrates operational applicability. This work establishes a foundational step toward building resilient, proactive, and autonomous supply chains capable of managing disruptions across deep-tier networks.

Problem

• supply chain disruption
• multi-tier visibility
• upstream vulnerability
• proactive resilience
• supply network monitoring

Innovation

• Agentic AI
• Supply Chain Resilience
• Multi-tier Supplier Mapping
• Autonomous Disruption Monitoring
• Large Language Models