Three AI-agents walk into a bar . . . . `Lord of the Flies' tribalism emerges among smart AI-Agents
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914353828069376 |
|---|---|
| author | Mori, Dhwanil M. Johnson, Neil F. |
| author_facet | Mori, Dhwanil M. Johnson, Neil F. |
| contents | Near-future infrastructure systems may be controlled by autonomous AI agents that repeatedly request access to limited resources such as energy, bandwidth, or computing power. We study a simplified version of this setting using a framework where N AI-agents independently decide at each round whether to request one unit from a system with fixed capacity C. An AI version of "Lord of the Flies" arises in which controlling tribes emerge with their own collective character and identity. The LLM agents do not reduce overload or improve resource use, and often perform worse than if they were flipping coins to make decisions. Three main tribal types emerge: Aggressive (27.3%), Conservative (24.7%), and Opportunistic (48.1%). The more capable AI-agents actually increase the rate of systemic failure. Overall, our findings show that smarter AI-agents can behave dumber as a result of forming tribes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_23093 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Three AI-agents walk into a bar . . . . `Lord of the Flies' tribalism emerges among smart AI-Agents Mori, Dhwanil M. Johnson, Neil F. Artificial Intelligence Social and Information Networks Physics and Society Near-future infrastructure systems may be controlled by autonomous AI agents that repeatedly request access to limited resources such as energy, bandwidth, or computing power. We study a simplified version of this setting using a framework where N AI-agents independently decide at each round whether to request one unit from a system with fixed capacity C. An AI version of "Lord of the Flies" arises in which controlling tribes emerge with their own collective character and identity. The LLM agents do not reduce overload or improve resource use, and often perform worse than if they were flipping coins to make decisions. Three main tribal types emerge: Aggressive (27.3%), Conservative (24.7%), and Opportunistic (48.1%). The more capable AI-agents actually increase the rate of systemic failure. Overall, our findings show that smarter AI-agents can behave dumber as a result of forming tribes. |
| title | Three AI-agents walk into a bar . . . . `Lord of the Flies' tribalism emerges among smart AI-Agents |
| topic | Artificial Intelligence Social and Information Networks Physics and Society |
| url | https://arxiv.org/abs/2602.23093 |