Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based Communities
Ryosuke Takata, Atsushi Masumori, Takashi Ikegami · 2024
Read Spontaneous Emergence of Agent Individuality Through Social Interactions in Large Language Model-Based Communities by Ryosuke Takata, Atsushi Masumori, Takashi Ikegami (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11675631.txt.
Description
Ryosuke Takata, Atsushi Masumori, and Takashi Ikegami explore in this 2024 study whether AI agents can grow distinct personalities just by talking. Past work gave each agent a fixed character and memory from the start. Here, agents based on large language models begin alike and chat in a group simulation. The question is whether differences appear on their own.
The agents traded natural language messages and formed loose communities. To keep chats going, they invented hashtags and even false claims. Their word choices grew more varied over time, and their moods shifted with each exchange. Personalities seemed to emerge and change as groups formed. The authors say this setup offers a new way to study how collective behavior arises in artificial groups.
Catalog record
| CREATOR | Ryosuke Takata, Atsushi Masumori, Takashi Ikegami |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 33 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |