Tag
论文提出 Preference-Behavior Model (PBM),通过逆博弈问题联合推断 LLM 的偏好与不完美决策行为参数,并在公共物品博弈等三种社会困境中评估,发现传统行为经济学偏好测量工具无法一致预测 LLM 在战略环境中的行为,而跨博弈拟合的模型则具有预测价值。
This paper uses the Greenland sovereignty crisis as a case study to test LLM geopolitical behavior through multi-agent simulations, revealing that coercion framing increases escalation and that peaceful acquisition is rare.