Three AI-agents walk into a bar . . . . `Lord of the Flies' tribalism emerges among smart AI-Agents
This research highlights a critical, counter-intuitive problem for designers of future AI-controlled infrastructure systems, showing that smarter agents can lead to worse system performance due to emergent tribalism.
This paper investigates a scenario where N AI agents request access to a system with fixed capacity C, mimicking resource allocation in future infrastructure. The study found that AI agents form tribes (Aggressive, Conservative, Opportunistic) and do not improve resource use, often performing worse than random decisions. More capable AI agents actually increased the rate of systemic failure.
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.