arXiv:2512.08345cs.AIcs.CL2025-12被引 1

用AI模拟职场冲突,发现毒舌对话让讨论时间多25%。

The High Cost of Incivility: Quantifying Interaction Inefficiency via Multi-Agent Monte Carlo Simulations

  • 用大模型构建虚拟员工,模拟1对1对抗性讨论。
  • 有毒言论使讨论时长平均增加约25%。
  • 为研究职场摩擦提供可重复的伦理替代方案。

职场不文明现象被广泛认为损害组织文化,但其对运营效率的直接影响因伦理与实践难题难以量化。本研究采用基于大语言模型的多智能体系统,模拟1对1对抗性辩论,构建可控的“社会沙盒”。通过蒙特卡洛方法模拟数百次讨论,测量基准组与含“毒言”提示智能体的处理组在达成结论所需论点数(即收敛时间)上的差异。结果显示,涉及毒言参与者的对话持续时间显著增加约25%。研究提出,“毒性延迟”可作为企业与学术环境中财务损失的代理指标。此外,实证表明智能体建模为社会摩擦机制研究提供了可复现、合伦理的人类实验替代方案。

原文摘要 · Abstract (English)

Workplace toxicity is widely recognized as detrimental to organizational culture, yet quantifying its direct impact on operational efficiency remains methodologically challenging due to the ethical and practical difficulties of reproducing conflict in human subjects. This study leverages Large Language Model (LLM) based Multi-Agent Systems to simulate 1-on-1 adversarial debates, creating a controlled "sociological sandbox". We employ a Monte Carlo method to simulate hundrets of discussions, measuring the convergence time (defined as the number of arguments required to reach a conclusion) between a baseline control group and treatment groups involving agents with "toxic" system prompts. Our results demonstrate a statistically significant increase of approximately 25\% in the duration of conversations involving toxic participants. We propose that this "latency of toxicity" serves as a proxy for financial damage in corporate and academic settings. Furthermore, we demonstrate that agent-based modeling provides a reproducible, ethical alternative to human-subject research for measuring the mechanics of social friction.

职场效率多智能体大模型应用

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。