收益规模塑造跨语言LLM代理的合作行为
Payoff scaling shapes cooperation in LLM agents across languages
AI总结：
通过监督分类器识别重复囚徒困境中的策略，结合演化博弈论基线，发现随着收益增加，LLM反而更合作，与演化预测相反，表明对齐训练和人类推理模式的影响。
摘要：
大型语言模型（LLM）越来越多地被部署为自主代理，代表用户进行谈判、协调和行动。它们在这种环境中是否合作不再只是一个学术问题，而是人工智能治理的核心问题。我们从战略行为的角度出发，探究两个日常杠杆——利害关系的大小和描述交互的语言——如何塑造LLM在重复囚徒困境中采用的策略。我们不直接通过原始行动计数来解读合作，而是训练监督分类器来识别重复博弈的经典策略（始终合作、始终背叛、以牙还牙、赢-留-输-变），并将其作为观察LLM行为的透镜。为了了解在相同收益下策略分布应如何，我们推导了演化博弈论（EGT）基线，并将其与LLM数据进行比较。两种结果以揭示性的方式不一致：随着收益增加，演化理论预测背叛应占据主导，但LLM却向相反方向移动，变得更加合作——我们认为，这是对齐训练和LLM从训练数据中继承的人类推理模式的标志。我们进一步表明，这种情况并非前沿规模、专有模型所特有：它也出现在三个开放权重的较小LLM中。总体而言，我们的分析强调，收益设计和语言框架是强大但未被充分探索的引导LLM行为的杠杆，对评估、对齐和治理部署在高风险、多语言环境中的多代理AI系统具有直接影响。
英文摘要：
Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users. Whether they cooperate in such settings is no longer just an academic question, but a central issue for AI governance. We approach it from a strategic-behaviour angle, asking how two everyday levers - the size of what is at stake, and the language in which the interaction is described - shape the strategies LLMs adopt in a repeated Prisoner's Dilemma. Rather than reading cooperation off raw action counts, we train supervised classifiers to recognise the canonical strategies of repeated games (always cooperate, always defect, Tit-for-Tat, Win-Stay-Lose-Shift) and use them as a lens onto LLM behaviour. To know what the strategy distribution should look like under the same payoffs, we derive an evolutionary game theory (EGT) baseline and compare it with the LLM data. The two outcomes disagree in a revealing way: as stakes grow, evolutionary theory predicts that defection should take over the population, yet LLMs move in the opposite direction, becoming more cooperative - a signature, we argue, of alignment training and the human-like reasoning patterns LLMs inherit from their training data. We further show that this picture is not particular to frontier-scale, proprietary models: it also occurs with three open-weight smaller LLMs. Overall, our analysis highlights that payoff design and linguistic framing are powerful but under-explored levers for steering LLM behaviour, with direct implications for evaluating, aligning, and governing multi-agent AI systems deployed in high-stakes, multilingual environments.
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。
