Spontaneous Emergence of Agent Individuality through Social Interactions in LLM-Based Communities

TL;DR

This paper demonstrates how social interactions among LLM-based agents can spontaneously lead to the emergence of individual personalities, behaviors, and social norms without predefined traits, revealing insights into collective AI development.

Contribution

It introduces a novel multi-agent simulation where LLM agents develop individuality through natural language interactions, without prior personality definitions.

Findings

Agents generate hallucinations and hashtags to sustain communication

Emotions and personalities of agents evolve through interactions

Diversity of words increases as agents form communities

Abstract

We study the emergence of agency from scratch by using Large Language Model (LLM)-based agents. In previous studies of LLM-based agents, each agent's characteristics, including personality and memory, have traditionally been predefined. We focused on how individuality, such as behavior, personality, and memory, can be differentiated from an undifferentiated state. The present LLM agents engage in cooperative communication within a group simulation, exchanging context-based messages in natural language. By analyzing this multi-agent simulation, we report valuable new insights into how social norms, cooperation, and personality traits can emerge spontaneously. This paper demonstrates that autonomously interacting LLM-powered agents generate hallucinations and hashtags to sustain communication, which, in turn, increases the diversity of words within their interactions. Each agent's emotions shift through communication, and as they form communities, the personalities of the agents emerge and evolve accordingly. This computational modeling approach and its findings will provide a new method for analyzing collective artificial intelligence.