InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains

TL;DR

InvAgent introduces a novel multi-agent system utilizing large language models for adaptive, explainable, and efficient inventory management in supply chains, outperforming traditional methods in resilience and cost reduction.

Contribution

This work pioneers the use of LLMs as autonomous agents in multi-agent inventory management, enabling zero-shot learning and dynamic adaptability in supply chain scenarios.

Findings

Improved resilience and efficiency in inventory management.

Reduced costs and prevented stockouts.

Effective handling of varying demand scenarios.

Abstract

Supply chain management (SCM) involves coordinating the flow of goods, information, and finances across various entities to deliver products efficiently. Effective inventory management is crucial in today's volatile and uncertain world. Previous research has demonstrated the superiority of heuristic methods and reinforcement learning applications in inventory management. However, the application of large language models (LLMs) as autonomous agents in multi-agent systems for inventory management remains underexplored. This study introduces a novel approach using LLMs to manage multi-agent inventory systems. Leveraging their zero-shot learning capabilities, our model, InvAgent, enhances resilience and improves efficiency across the supply chain network. Our contributions include utilizing LLMs for zero-shot learning to enable adaptive and informed decision-making without prior training, providing explainability and clarity through chain-of-thought, and demonstrating dynamic adaptability to varying demand scenarios while reducing costs and preventing stockouts. Extensive evaluations across different scenarios highlight the efficiency of our model in SCM.