用大模型模拟供应链多阶段决策，发现认知差异会加剧效率问题。
Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation
- 用不同认知水平的LLM代理模拟供应链层级互动
- 发现代理存在短视自私行为，导致系统效率下降
- 信息共享能有效缓解负面影响，适合研究AI组织决策
在复杂多轮决策中建模生成式智能体的协调是人工智能与运营管理的核心挑战。尽管行为实验揭示了供应链低效背后的认知偏差，但传统方法面临可扩展性和控制力不足的问题。本文提出一种基于大型语言模型（LLMs）的可扩展实验范式，模拟多阶段供应链动态。依托分层推理框架，本研究特别分析认知异质性对智能体交互的影响。不同于以往同质化设置，我们采用DeepSeek和GPT代理，在供应链各层级系统性地改变推理复杂度。通过严格重复且统计验证的仿真，研究这种认知多样性如何影响集体结果。结果显示，智能体表现出短视和自利行为，加剧系统性低效；然而，我们证明信息共享能有效缓解这些负面效应。研究拓展了传统行为方法，为智能体驱动组织的动态提供了新见解。该工作强调了基于LLM的智能体在复杂运营环境中作为人类决策代理的潜力与局限。
原文摘要 · Abstract (English)
Modeling coordination among generative agents in complex multi-round decision-making presents a core challenge for AI and operations management. Although behavioral experiments have revealed cognitive biases behind supply chain inefficiencies, traditional methods face scalability and control limitations. We introduce a scalable experimental paradigm using Large Language Models (LLMs) to simulate multi-stage supply chain dynamics. Grounded in a Hierarchical Reasoning Framework, this study specifically analyzes the impact of cognitive heterogeneity on agent interactions. Unlike prior homogeneous settings, we employ DeepSeek and GPT agents to systematically vary reasoning sophistication across supply chain tiers. Through rigorously replicated and statistically validated simulations, we investigate how this cognitive diversity influences collective outcomes. Results indicate that agents exhibit myopic and self-interested behaviors that exacerbate systemic inefficiencies. However, we demonstrate that information sharing effectively mitigates these adverse effects. Our findings extend traditional behavioral methods and offer new insights into the dynamics of AI-enabled organizations. This work underscores both the potential and limitations of LLM-based agents as proxies for human decision-making in complex operational environments.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。