Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory

Gordon Dai, Weijia Zhang, Jinhan Li, Siqi Yang, Chidera Onochie lbe, Srihas Rao, Arthur Caetano, Misha Sra

TL;DR

The paper investigates whether LLM-driven agents under resource scarcity exhibit Hobbesian social evolution, transitioning from a state of nature marked by conflict to a commonwealth governed by an absolute sovereign. It introduces a modular generative-agent framework where agents possess quantifiable traits, constrained memory, and four actions (Farm, Rob, Trade, Donate) within a sandbox environment. Through systematic experiments that vary agent and system parameters, the study finds robust transitions toward social order and provides insights into how memory depth and intelligence influence convergence and cooperation. While showing promise for modeling complex social dynamics with LLMs, the work also acknowledges limitations in token constraints, scalability, and the fidelity of psychological representations, suggesting avenues for deeper exploration in AI-enabled social science.

Abstract

The emergence of Large Language Models (LLMs) and advancements in Artificial Intelligence (AI) offer an opportunity for computational social science research at scale. Building upon prior explorations of LLM agent design, our work introduces a simulated agent society where complex social relationships dynamically form and evolve over time. Agents are imbued with psychological drives and placed in a sandbox survival environment. We conduct an evaluation of the agent society through the lens of Thomas Hobbes's seminal Social Contract Theory (SCT). We analyze whether, as the theory postulates, agents seek to escape a brutish "state of nature" by surrendering rights to an absolute sovereign in exchange for order and security. Our experiments unveil an alignment: Initially, agents engage in unrestrained conflict, mirroring Hobbes's depiction of the state of nature. However, as the simulation progresses, social contracts emerge, leading to the authorization of an absolute sovereign and the establishment of a peaceful commonwealth founded on mutual cooperation. This congruence between our LLM agent society's evolutionary trajectory and Hobbes's theoretical account indicates LLMs' capability to model intricate social dynamics and potentially replicate forces that shape human societies. By enabling such insights into group behavior and emergent societal phenomena, LLM-driven multi-agent simulations, while unable to simulate all the nuances of human behavior, may hold potential for advancing our understanding of social structures, group dynamics, and complex human systems.

Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory

TL;DR

The paper investigates whether LLM-driven agents under resource scarcity exhibit Hobbesian social evolution, transitioning from a state of nature marked by conflict to a commonwealth governed by an absolute sovereign. It introduces a modular generative-agent framework where agents possess quantifiable traits, constrained memory, and four actions (Farm, Rob, Trade, Donate) within a sandbox environment. Through systematic experiments that vary agent and system parameters, the study finds robust transitions toward social order and provides insights into how memory depth and intelligence influence convergence and cooperation. While showing promise for modeling complex social dynamics with LLMs, the work also acknowledges limitations in token constraints, scalability, and the fidelity of psychological representations, suggesting avenues for deeper exploration in AI-enabled social science.

Abstract

The emergence of Large Language Models (LLMs) and advancements in Artificial Intelligence (AI) offer an opportunity for computational social science research at scale. Building upon prior explorations of LLM agent design, our work introduces a simulated agent society where complex social relationships dynamically form and evolve over time. Agents are imbued with psychological drives and placed in a sandbox survival environment. We conduct an evaluation of the agent society through the lens of Thomas Hobbes's seminal Social Contract Theory (SCT). We analyze whether, as the theory postulates, agents seek to escape a brutish "state of nature" by surrendering rights to an absolute sovereign in exchange for order and security. Our experiments unveil an alignment: Initially, agents engage in unrestrained conflict, mirroring Hobbes's depiction of the state of nature. However, as the simulation progresses, social contracts emerge, leading to the authorization of an absolute sovereign and the establishment of a peaceful commonwealth founded on mutual cooperation. This congruence between our LLM agent society's evolutionary trajectory and Hobbes's theoretical account indicates LLMs' capability to model intricate social dynamics and potentially replicate forces that shape human societies. By enabling such insights into group behavior and emergent societal phenomena, LLM-driven multi-agent simulations, while unable to simulate all the nuances of human behavior, may hold potential for advancing our understanding of social structures, group dynamics, and complex human systems.
Paper Structure (47 sections, 7 figures, 1 table)

This paper contains 47 sections, 7 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Traditional Computer-Based Social Simulations
  4. LLM-Based Simulations
  5. Interactive LLMs
  6. Group Dynamics
  7. Generative Agent Design and Behavior
  8. Setting
  9. Agents
  10. Traits:
  11. Memory:
  12. Context:
  13. Actions
  14. Farm:
  15. Rob:
  16. ...and 32 more sections

Figures (7)

  • Figure 1: Our interactive user interface; the left-hand side displays the attributes (aggressiveness, strength, etc.) of Agent 2, current resources (food and land), relationships with other agents and information about their current and pending actions, and memory; the right-hand side shows the simulation log with each action documented as an emoji.
  • Figure 2: The flowchart shows the flow of the simulation in a "day" where each agent takes turns to perform actions and respond to actions performed by other agents.
  • Figure 3: Transforming from a State of Nature to a Commonwealth
  • Figure 4: Change in Ratios of Robbery, Trade, and Farm wrt Time; a commonwealth is formed on Day 21 in this trial/run.
  • Figure 5: Agent behavior before (in black) and after (in grey) the commonwealth forms.
  • ...and 2 more figures