Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Generative Organizational Behavior Simulation using Large Language Model based Autonomous Agents: A Holacracy Perspective

Chen Zhu, Yihang Cheng, Jingshuai Zhang, Yusheng Qiu, Sitao Xia, Hengshu Zhu

TL;DR

This paper tackles how Holacracy dynamics can be studied with an LLM-based autonomous-agent simulator, introducing CareerAgent and a three-phase workflow (Construction, Execution, Evaluation) to model a Holacracy organization. Through eight weeks of simulated rounds, it demonstrates that higher average competence lowers stress but can reduce organization-wide task completion, while individuals with higher competence show improved completion and occupy central positions in evolving social networks. The results reveal that competent members self-select tasks and form sub-communities, offering theoretical insights into decentralized governance and practical guidance for managing holacratic organizations. The framework enables flexible parameter experimentation and provides an experimental foundation for future studies of Holacracy and related organizational dynamics.

Abstract

In this paper, we present the technical details and periodic findings of our project, CareerAgent, which aims to build a generative simulation framework for a Holacracy organization using Large Language Model-based Autonomous Agents. Specifically, the simulation framework includes three phases: construction, execution, and evaluation, and it incorporates basic characteristics of individuals, organizations, tasks, and meetings. Through our simulation, we obtained several interesting findings. At the organizational level, an increase in the average values of management competence and functional competence can reduce overall members' stress levels, but it negatively impacts deeper organizational performance measures such as average task completion. At the individual level, both competences can improve members' work performance. From the analysis of social networks, we found that highly competent members selectively participate in certain tasks and take on more responsibilities. Over time, small sub-communities form around these highly competent members within the holacracy. These findings contribute theoretically to the study of organizational science and provide practical insights for managers to understand the organization dynamics.

Generative Organizational Behavior Simulation using Large Language Model based Autonomous Agents: A Holacracy Perspective

TL;DR

This paper tackles how Holacracy dynamics can be studied with an LLM-based autonomous-agent simulator, introducing CareerAgent and a three-phase workflow (Construction, Execution, Evaluation) to model a Holacracy organization. Through eight weeks of simulated rounds, it demonstrates that higher average competence lowers stress but can reduce organization-wide task completion, while individuals with higher competence show improved completion and occupy central positions in evolving social networks. The results reveal that competent members self-select tasks and form sub-communities, offering theoretical insights into decentralized governance and practical guidance for managing holacratic organizations. The framework enables flexible parameter experimentation and provides an experimental foundation for future studies of Holacracy and related organizational dynamics.

Abstract

In this paper, we present the technical details and periodic findings of our project, CareerAgent, which aims to build a generative simulation framework for a Holacracy organization using Large Language Model-based Autonomous Agents. Specifically, the simulation framework includes three phases: construction, execution, and evaluation, and it incorporates basic characteristics of individuals, organizations, tasks, and meetings. Through our simulation, we obtained several interesting findings. At the organizational level, an increase in the average values of management competence and functional competence can reduce overall members' stress levels, but it negatively impacts deeper organizational performance measures such as average task completion. At the individual level, both competences can improve members' work performance. From the analysis of social networks, we found that highly competent members selectively participate in certain tasks and take on more responsibilities. Over time, small sub-communities form around these highly competent members within the holacracy. These findings contribute theoretically to the study of organizational science and provide practical insights for managers to understand the organization dynamics.
Paper Structure (16 sections, 15 equations, 3 figures, 5 tables)

This paper contains 16 sections, 15 equations, 3 figures, 5 tables.

Table of Contents

  1. Introduction
  2. The process and key concepts of holacracy
  3. LLM-based simulation platform for holacracy
  4. Construction phase
  5. Execution phase
  6. Evaluation phase
  7. Experimental design
  8. Research issues
  9. Parameter design and variable measurements
  10. Individual
  11. Organization
  12. Experimental implementation
  13. Results
  14. Empirical analyses
  15. Social network analysis
  16. ...and 1 more sections

Figures (3)

  • Figure 1: Generative agents in an organization
  • Figure 2: Simulation framework overview
  • Figure 3: Social network condition at the end of the eighth week