Leveraging LLM-Based Agents for Intelligent Supply Chain Planning

2025-09-03

AI Summary

To address persistent challenges in e-commerce supply chain long-term planning—including difficulty in dynamic re-planning, low interpretability, and high reliance on manual intervention—this paper proposes an intelligent agent framework powered by large language models (LLMs). The framework integrates domain knowledge injection, autonomous multi-granularity task decomposition, tool-augmented API invocation, and chain-of-evidence reasoning to enable end-to-end automation and dynamic re-planning for demand forecasting, inventory optimization, and replenishment decision-making. Its key innovation lies in constructing traceable and verifiable decision evidence chains, substantially enhancing planning transparency and adaptive responsiveness. Deployed in JD.com’s real-world operational environment, the framework reduced manual intervention by 42%, decreased demand forecasting MAPE by 18.3%, improved in-stock rate by 5.7 percentage points, and increased overall operational efficiency by 23.1%.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

In supply chain management, planning is a critical concept. The movement of physical products across different categories, from suppliers to warehouse management, to sales, and logistics transporting them to customers, entails the involvement of many entities. It covers various aspects such as demand forecasting, inventory management, sales operations, and replenishment. How to collect relevant data from an e-commerce platform's perspective, formulate long-term plans, and dynamically adjust them based on environmental changes, while ensuring interpretability, efficiency, and reliability, is a practical and challenging problem. In recent years, the development of AI technologies, especially the rapid progress of large language models, has provided new tools to address real-world issues. In this work, we construct a Supply Chain Planning Agent (SCPA) framework that can understand domain knowledge, comprehend the operator's needs, decompose tasks, leverage or create new tools, and return evidence-based planning reports. We deploy this framework in JD.com's real-world scenario, demonstrating the feasibility of LLM-agent applications in the supply chain. It effectively reduced labor and improved accuracy, stock availability, and other key metrics.

Problem

• Optimizing supply chain planning with dynamic adjustments
• Enhancing interpretability and efficiency in logistics operations
• Integrating LLM agents for data-driven decision making

Innovation

• LLM-based agent framework for supply chain planning
• Decomposes tasks and creates tools dynamically
• Integrates domain knowledge with operator needs