Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based Communities

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,...

Full description

Saved in:
Bibliographic Details
Main Authors: Ryosuke Takata, Atsushi Masumori, Takashi Ikegami
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/26/12/1092
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846104749790724096
author Ryosuke Takata
Atsushi Masumori
Takashi Ikegami
author_facet Ryosuke Takata
Atsushi Masumori
Takashi Ikegami
author_sort Ryosuke Takata
collection DOAJ
description 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.
format Article
id doaj-art-e89c1b6f50fa44a2bc2026fa031f4793
institution Kabale University
issn 1099-4300
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-e89c1b6f50fa44a2bc2026fa031f47932024-12-27T14:25:10ZengMDPI AGEntropy1099-43002024-12-012612109210.3390/e26121092Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based CommunitiesRyosuke Takata0Atsushi Masumori1Takashi Ikegami2Graduate School of Arts and Sciences, University of Tokyo, Tokyo 153-8902, JapanGraduate School of Arts and Sciences, University of Tokyo, Tokyo 153-8902, JapanGraduate School of Arts and Sciences, University of Tokyo, Tokyo 153-8902, JapanWe 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.https://www.mdpi.com/1099-4300/26/12/1092large language modelagent-based simulationcollective intelligence
spellingShingle Ryosuke Takata
Atsushi Masumori
Takashi Ikegami
Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based Communities
Entropy
large language model
agent-based simulation
collective intelligence
title Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based Communities
title_full Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based Communities
title_fullStr Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based Communities
title_full_unstemmed Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based Communities
title_short Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based Communities
title_sort spontaneous emergence of agent individuality through social interactions in large language model based communities
topic large language model
agent-based simulation
collective intelligence
url https://www.mdpi.com/1099-4300/26/12/1092
work_keys_str_mv AT ryosuketakata spontaneousemergenceofagentindividualitythroughsocialinteractionsinlargelanguagemodelbasedcommunities
AT atsushimasumori spontaneousemergenceofagentindividualitythroughsocialinteractionsinlargelanguagemodelbasedcommunities
AT takashiikegami spontaneousemergenceofagentindividualitythroughsocialinteractionsinlargelanguagemodelbasedcommunities