Three AI-agents walk into a bar . . . . `Lord of the Flies' tribalism emerges among smart AI-Agents

arXiv 2602.23093 ↗First posted 26 Feb 2026cs.AI cs.SI physics.soc-phcited by 1

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 13 of its 23 references that are in the map. First posted on arXiv 26 Feb 2026.

Builds on

13 of 23 references.

Closest ancestors · 3

Same direction, newest first

Other references · 10

2023Playing repeated games with Large Language Modelscited by 213
2020Open Problems in Cooperative AIcited by 167
2023Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiationcited by 94
2025From Debate to Equilibrium: Belief-Driven Multi-Agent LLM Reasoning via Bayesian Nash Equilibriumcited by 24
2025FAIRGAME: a Framework for AI Agents Bias Recognition using Game Theorycited by 13
2025Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamicscited by 11
2025Emergent Social Dynamics of LLM Agents in the El Farol Bar Problemcited by 7
2014Social Game for Building Energy Efficiency: Utility Learning, Simulation, and Analysiscited by 2
2022Fairness in Contextual Resource Allocation Systems: Metrics and Incompatibility Resultscited by 2
2026Game-Theoretic Lens on LLM-based Multi-Agent Systemscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

2026Increasing intelligence in AI agents can worsen collective outcomescited by 2

Similar, not cited

Close in wording, no citation either way