认知异质性动力学：基于大语言模型模拟的多阶段供应链中行为偏差研究
Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation
AI总结：
本文通过引入大语言模型模拟多阶段供应链，基于分层推理框架分析认知异质性对智能体交互的影响，发现信息共享可缓解短视和自利行为导致的系统效率低下。
摘要：
在复杂的多轮决策中，生成式智能体之间的协调建模是人工智能和运营管理的核心挑战。尽管行为实验揭示了供应链效率低下背后的认知偏差，但传统方法面临可扩展性和控制限制。我们引入了一种可扩展的实验范式，使用大语言模型（LLMs）模拟多阶段供应链动态。本研究基于分层推理框架，专门分析了认知异质性对智能体交互的影响。与先前的同质设置不同，我们采用DeepSeek和GPT智能体，系统性地改变供应链各层级的推理复杂度。通过严格重复和统计验证的模拟，我们研究了这种认知多样性如何影响集体结果。结果表明，智能体表现出短视和自利行为，加剧了系统效率低下。然而，我们证明信息共享有效缓解了这些不利影响。我们的发现扩展了传统行为方法，并为AI赋能组织的动态提供了新见解。这项工作强调了基于LLM的智能体作为人类决策代理在复杂运营环境中的潜力和局限性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
