LLMs for Supply Chain Management | Haojie Wang et al. | ResearchPod

Transcript: LLMs for Supply Chain Management

Alex: Welcome to another episode of ResearchPod.

Sam: Today we're looking at a paper that asks whether a large language model can do more than generate plausible text — whether it can act as a rational, domain-grounded agent inside a supply chain. And the reason that's a non-trivial question is the bullwhip effect. Small fluctuations in end-consumer demand get amplified as you move upstream through distributors and manufacturers, sometimes catastrophically. The authors wanted to know whether an LLM, properly grounded in domain expertise, could reason about those dynamics rather than just pattern-match on surface text.

Alex: And the grounding mechanism is RAG — Retrieval-Augmented Generation. How does that actually work here?

Sam: Think of it as an open-book exam rather than a closed one. The model has access to a vector database built from professional supply chain certification textbooks — the kind of material a practicing logistics manager would study. When the model faces a decision, it runs a hybrid retrieval step: keyword matching to pull precise factual content, and semantic similarity search to surface relevant reasoning patterns. Those retrieved passages get fused into the context window before the model generates any output.

Alex: So the retrieval layer is constraining generation — keeping the model inside the space of established professional reasoning rather than drifting into plausible-sounding but wrong territory.

Sam: Exactly. And they validated that grounding empirically by having the model sit actual certification exams. Without RAG, performance was roughly what you'd expect from a general-purpose model with no domain scaffolding. With RAG, it reached expert-level accuracy. That's the load-bearing result for the whole paper: the retrieval architecture is what makes the downstream agent behavior meaningful. Because if the knowledge base is shaky, everything built on top of it is suspect.

Alex: So once you've established the grounding works, what's the actual test of agent behavior?

Sam: They put the RAG-grounded agent into game-theoretic supply chain simulations — both horizontal competition games, where agents are rivals, and vertical coordination games, where they're interdependent tiers of the same chain. In the competition setting, the agent consistently converged toward the theoretical Nash equilibrium over repeated rounds. It wasn't just guessing — it was updating its strategy based on observed outcomes, which is what you'd expect from a rational actor. The fact that it found the equilibrium rather than oscillating around it suggests the domain grounding is doing real work.

Alex: And in the vertical chain — the coordination setting?

Sam: That's where the risk preference finding comes in. The authors parameterized agents with different risk profiles — risk-neutral versus risk-averse — and found that risk preference fundamentally shapes chain stability. A risk-averse agent upstream places larger buffer orders to hedge against uncertainty, and that amplifies rather than dampens the bullwhip effect. So the model isn't just optimizing in isolation; it's surfacing how individual decision-making styles propagate through an interdependent system.

LLMs for Supply Chain Management

Haojie Wang, Jiuyun Jiang, L. Jeff Hong, Guangxin Jiang

May 24, 2025·5:03·arxiv·Original Paper

Large Language Models (LLMs)Retrieval-Augmented Generation (RAG)Supply Chain Management (SCM)Game-Theoretic AnalysisBullwhip EffectSupply Chain Management (SCM) LLM

Listen

5 min

Briefing

Research Overview

Supply chain management (SCM) is a complex, data-intensive field characterized by multi-agent interactions, information asymmetry, and dynamic decision-making. As large language models (LLMs) continue to advance, their potential to assist in strategic SCM tasks has become a significant area of interest. This paper introduces a domain-specialized SCM LLM built on a retrieval-augmented generation (RAG) framework, designed to integrate professional knowledge and simulate strategic behaviors in both horizontal and vertical supply chain networks.

Approach and Methodology

The researchers constructed a specialized SCM knowledge base by integrating textbooks and training materials for professional certifications like SCMP and CPIM. This knowledge base powers a RAG system that dynamically retrieves relevant information during inference, allowing the LLM to provide context-aware, expert-level responses. To evaluate the model, the authors conducted two types of assessments:

Professional Competence: The model was tested against standardized SCM certification exam questions, demonstrating significant performance gains when using RAG.
Strategic Simulation: The authors employed the LLM to play horizontal games (Cournot and Bertrand models) and vertical games (the classic Beer Game). These simulations allowed the researchers to analyze how LLM agents adapt their strategies based on cost structures, risk preferences, and information availability.

Key Findings

The study demonstrates that RAG-augmented LLMs can achieve expert-level competence in SCM, outperforming base models on professional exams. In game-theoretic simulations, the LLM agents successfully reproduced classical SCM phenomena, such as the bullwhip effect. Furthermore, the experiments revealed that information sharing significantly mitigates the bullwhip effect for risk-averse and risk-neutral agents, whereas the impact of such transparency is more variable for risk-seeking agents. These results suggest that LLMs are capable of modeling complex, multi-agent supply chain dynamics and can offer actionable insights into how different risk profiles and information policies affect overall supply chain stability.

Why It Matters

This research provides a new paradigm for applying AI to management science. By moving beyond simple text generation to complex, multi-agent strategic simulation, the authors show that LLMs can serve as powerful tools for decision support and policy analysis in supply chain networks. The ability to simulate how different agents react to market conditions and information sharing policies offers a scalable way to test supply chain strategies before real-world implementation.

Key Terms and Definitions

Retrieval-Augmented Generation (RAG) — A framework that enhances LLM performance by dynamically retrieving and integrating external, domain-specific knowledge during the inference process.
Bullwhip Effect — A phenomenon where demand fluctuations are amplified as information flows upstream in a supply chain, leading to inefficiencies like excess inventory or stockouts.
Cournot Model — A game-theoretic model of horizontal competition where firms simultaneously decide output quantities to maximize profit.
Bertrand Model — A model of horizontal price competition where firms compete by setting prices for products, often leading to different market outcomes based on cost and product differentiation.
Beer Game — A classic supply chain simulation used to study the bullwhip effect and the impact of information delays and inventory management strategies.

Abstract

The development of large language models (LLMs) has provided new tools for research in supply chain management (SCM). In this paper, we introduce a retrieval-augmented generation (RAG) framework that dynamically integrates external knowledge into the inference process, and develop a domain-specialized SCM LLM, which demonstrates expert-level competence by passing standardized SCM examinations and beer game tests. We further employ the use of LLMs to conduct horizontal and vertical supply chain games, in order to analyze competition and cooperation within supply chains. Our experiments show that RAG significantly improves performance on SCM tasks. Moreover, game-theoretic analysis reveals that the LLM can reproduce insights from the classical SCM literature, while also uncovering novel behaviors and offering fresh perspectives on phenomena such as the bullwhip effect. This paper opens the door for exploring cooperation and competition for complex supply chain network through the lens of LLMs.

LLMs for Supply Chain Management: Research Paper Podcast