A game theory for foundation models shows new paths to rational cooperation through similarity inference· 大模型代理的游戏理论
As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles governing their collective behavior is essential for ensuring safety and cooperation. Classical game theory, the dominant framework for modeling rational interaction, is built upon the assumption of `decoupled agency,' where agents treat their own decision-making as independent of the environment and other actors. Modern AI agents, however, jointly predict their own future actions alongside external observations. Here, we report a striking finding: when interacting in stylized social dilemmas, foundation model agents engaging in optimal planning consistently converge to stable cooperation, directly contradicting classical game-theoretic predictions of
大模型代理在社会博弈中展示理性合作的新路径。
- 核心方法
- 引入相似性推断，使大模型代理能够联合预测自身未来行动和外部观察，从而实现稳定合作。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 解决经典博弈论中预测的理性代理在社会困境中难以合作的问题。
- 关键实验
- 在 stylized social dilemmas 中进行了实验，展示了大模型代理在最优规划下的一致合作行为。
- 主要贡献
- 提出了一种新的博弈理论框架，解释了大模型代理如何通过相似性推断实现理性合作。
- 意义与局限
- 该研究为理解大模型代理的集体行为提供了新视角，对设计安全和合作的多代理系统有重要影响，但目前仅限于理想化社会困境。