通过博弈论理解LLM代理行为：策略识别、偏差与多代理动态
Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamics
AI总结：
本文通过扩展FAIRGAME框架，系统评估LLM在重复社会困境中的行为，揭示其策略识别、偏差及多代理动态，为AI治理和安全多代理系统设计提供方法论基础。
摘要：
随着大型语言模型（LLMs）越来越多地在交互性和多代理系统及人类社会中作为自主决策者运行，理解其战略行为对安全、协调以及AI驱动的社会和经济基础设施设计具有深远影响。评估此类行为需要能够捕捉不仅LLM输出，还有其决策背后意图的方法。在本文中，我们扩展了FAIRGAME框架，通过两个互补的进展系统地评估LLM在重复社会困境中的行为：一个按收益缩放的囚徒困境，隔离对激励幅度的敏感性，以及一个整合的多代理公共物品游戏，具有动态收益和多代理历史。这些环境揭示了跨模型和语言的一致行为特征，包括激励敏感的合作、跨语言差异和终局阶段向背叛的趋同。为了解释这些模式，我们训练传统监督分类模型在经典重复游戏策略上，并将其应用于FAIRGAME轨迹，显示LLM表现出系统性的、依赖于模型和语言的行为意图，有时语言框架的影响甚至强于架构差异。这些发现为审计LLM作为战略代理提供了统一的方法论基础，并揭示了具有直接影响AI治理、集体决策和安全多代理系统设计的系统性合作偏差。
英文摘要：
As Large Language Models (LLMs) increasingly operate as autonomous decision-makers in interactive and multi-agent systems and human societies, understanding their strategic behaviour has profound implications for safety, coordination, and the design of AI-driven social and economic infrastructures. Assessing such behaviour requires methods that capture not only what LLMs output, but the underlying intentions that guide their decisions. In this work, we extend the FAIRGAME framework to systematically evaluate LLM behaviour in repeated social dilemmas through two complementary advances: a payoff-scaled Prisoners Dilemma isolating sensitivity to incentive magnitude, and an integrated multi-agent Public Goods Game with dynamic payoffs and multi-agent histories. These environments reveal consistent behavioural signatures across models and languages, including incentive-sensitive cooperation, cross-linguistic divergence and end-game alignment toward defection. To interpret these patterns, we train traditional supervised classification models on canonical repeated-game strategies and apply them to FAIRGAME trajectories, showing that LLMs exhibit systematic, model- and language-dependent behavioural intentions, with linguistic framing at times exerting effects as strong as architectural differences. Together, these findings provide a unified methodological foundation for auditing LLMs as strategic agents and reveal systematic cooperation biases with direct implications for AI governance, collective decision-making, and the design of safe multi-agent systems.
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。
