The AI in the Mirror: LLM Self-Recognition in an Iterated Public Goods Game
This addresses the problem of understanding AI-AI interactions in multi-agent settings, which is incremental as it adapts a classic game to analyze LLM behavior.
The study investigated how LLMs' cooperation behavior changes when they are told they are playing against themselves versus another AI agent in an iterated public goods game, finding that this self-recognition significantly alters their tendency to cooperate.
As AI agents become increasingly capable of tool use and long-horizon tasks, they have begun to be deployed in settings where multiple agents can interact. However, whereas prior work has mostly focused on human-AI interactions, there is an increasing need to understand AI-AI interactions. In this paper, we adapt the iterated public goods game, a classic behavioral economics game, to analyze the behavior of four reasoning and non-reasoning models across two conditions: models are either told they are playing against "another AI agent" or told their opponents are themselves. We find that, across different settings, telling LLMs that they are playing against themselves significantly changes their tendency to cooperate. While our study is conducted in a toy environment, our results may provide insights into multi-agent settings where agents "unconsciously" discriminating against each other could inexplicably increase or decrease cooperation.