让大模型模拟国际危机决策，发现其行为随时间演变且缺乏对抗性思维。
LLMs as Strategic Actors: Behavioral Alignment, Risk Calibration, and Argumentation Framing in Geopolitical Simulations
- 在多轮地缘政治模拟中评估六款主流大模型的行为表现。
- 模型初期接近人类决策模式，但后期出现明显策略分化。
- 解释理由多强调稳定与合作，缺乏对抗性推理，适合安全风险分析。
大型语言模型（LLMs）被越来越多地视为战略决策环境中的代理，但其在结构化地缘政治模拟中的表现仍研究不足。我们评估了六款前沿的LLM，并与人类在四个真实世界危机模拟场景中的结果进行对比，要求模型在多轮中选择预定义行动并解释决策依据。通过行动一致性、行动严重性反映的风险校准以及基于国际关系理论的论证框架进行比较。结果显示，模型在基础模拟回合中近似人类决策模式，但在多轮后出现显著行为差异，表现出独特的行为特征和策略更新。所有模型对所选行动的解释均呈现强烈的规范性-合作性倾向，聚焦于稳定、协调与风险缓解，对抗性推理能力有限。
原文摘要 · Abstract (English)
Large language models (LLMs) are increasingly proposed as agents in strategic decision environments, yet their behavior in structured geopolitical simulations remains under-researched. We evaluate six popular state-of-the-art LLMs alongside results from human results across four real-world crisis simulation scenarios, requiring models to select predefined actions and justify their decisions across multiple rounds. We compare models to humans in action alignment, risk calibration through chosen actions' severity, and argumentative framing grounded in international relations theory. Results show that models approximate human decision patterns in base simulation rounds but diverge over time, displaying distinct behavioural profiles and strategy updates. LLM explanations for chosen actions across all models exhibit a strong normative-cooperative framing centered on stability, coordination, and risk mitigation, with limited adversarial reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。