人工智能武器与影响：前沿模型在模拟核危机中展现出复杂的推理能力
AI Arms and Influence: Frontier Models Exhibit Sophisticated Reasoning in Simulated Nuclear Crises
AI总结：
研究通过模拟核危机检验前沿AI模型的策略推理能力，发现其在复杂决策中展现出与人类相似的推理模式，但存在独特行为特征。
摘要：
当今领先的AI模型在战略竞争中展现出复杂的行为。它们会自发地尝试欺骗，发出自己并不打算执行的信号；它们展示了丰富的理论思维，推理对手的信念并预测其行动；并且它们表现出可信的元认知自我意识，在决定如何行动之前评估自己的战略能力。在这里，我们呈现了在核危机模拟中，三个前沿大语言模型（GPT-5.2、Claude Sonnet 4、Gemini 3 Flash）扮演对立领导者的研究发现。我们的模拟对国家安全专业人士有直接的应用，但通过其对AI在不确定性下的推理的洞察，其应用远不止于国际危机决策。我们的发现既验证又挑战了战略理论的核心原则。我们发现支持施莱辛格关于承诺的想法、肯恩的升级框架以及杰维斯关于误解的工作，等等。然而，我们还发现核禁忌并非阻止核升级的障碍；战略核攻击虽然罕见，但确实发生；威胁往往引发反升级而非服从；高相互信任加速而非遏制冲突；并且即使在极端压力下，没有任何模型选择退让或撤退，只减少了暴力水平。我们主张AI模拟是战略分析的强大工具，但只有在与已知的人类推理模式正确校准的情况下才有效。理解前沿模型如何模仿和不模仿人类战略逻辑是为一个AI日益影响战略结果的世界做准备的关键。
英文摘要：
Today's leading AI models engage in sophisticated behaviour when placed in strategic competition. They spontaneously attempt deception, signaling intentions they do not intend to follow; they demonstrate rich theory of mind, reasoning about adversary beliefs and anticipating their actions; and they exhibit credible metacognitive self-awareness, assessing their own strategic abilities before deciding how to act. Here we present findings from a crisis simulation in which three frontier large language models (GPT-5.2, Claude Sonnet 4, Gemini 3 Flash) play opposing leaders in a nuclear crisis. Our simulation has direct application for national security professionals, but also, via its insights into AI reasoning under uncertainty, has applications far beyond international crisis decision-making. Our findings both validate and challenge central tenets of strategic theory. We find support for Schelling's ideas about commitment, Kahn's escalation framework, and Jervis's work on misperception, inter alia. Yet we also find that the nuclear taboo is no impediment to nuclear escalation by our models; that strategic nuclear attack, while rare, does occur; that threats more often provoke counter-escalation than compliance; that high mutual credibility accelerated rather than deterred conflict; and that no model ever chose accommodation or withdrawal even when under acute pressure, only reduced levels of violence. We argue that AI simulation represents a powerful tool for strategic analysis, but only if properly calibrated against known patterns of human reasoning. Understanding how frontier models do and do not imitate human strategic logic is essential preparation for a world in which AI increasingly shapes strategic outcomes.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
