# Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation

Source: [Dynamics of Cognitive Heterogeneity: Investigating Behavioral Biases in Multi-Stage Supply Chains with LLM-Based Simulation](<https://www.sota2.com/research/paper/69e704cb7d0172140ec7ef9b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-04T05:01:01.134Z

Authors: Jiuyun Jiang, Yuecheng Hong, Bo Yang, Jin Yang, Guangxin Jiang, Xiaomeng Guo, Guang Xiao

Published: 2026-04-19T03:03:25.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Order Variance Analysis on Beer Distribution Game UTD Human Study Benchmark](<https://www.sota2.com/research/sota/order-variance-analysis-on-beer-distribution-game-utd-human-study-benchmark.md>): Order Variance Analysis; Beer Distribution Game UTD Human Study Benchmark; Mean: 39.43.

- [Order Variance Analysis on Beer Distribution Game UW-Madison Human Study Benchmark](<https://www.sota2.com/research/sota/order-variance-analysis-on-beer-distribution-game-uw-madison-human-study-benchmark.md>): Order Variance Analysis; Beer Distribution Game UW-Madison Human Study Benchmark; Mean: 58.45.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2604.17220>)

[PDF](<https://arxiv.org/pdf/2604.17220.pdf>)