发表机构
Fudan University（复旦大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过公共品博弈实验发现，多智能体上下文学习中的性能提升主要源于统计外推而非递归推理，并引入理性预期均衡作为诊断工具。
AI 中文摘要
上下文学习（ICL）使大型语言模型（LLM）智能体能够利用交互历史来改进决策，然而这种改进究竟反映了精细的内部推理，还是仅仅是对统计模式的外推，目前仍不清楚。为厘清这些机制，我们在需要递归信念推理的多智能体不完全信息博弈中研究LLM智能体。通过构建一个公共品博弈并操纵历史反馈的统计结构，我们以与历史无关的理性预期均衡（REE）基准来评估决策质量。实验表明，当历史统计模式被打乱时，较长上下文带来的收益基本消失，决策质量退化至无上下文基线水平，且这种退化随战略相互依赖性的增强而急剧放大。这些结果表明，在此类战略环境中，ICL行为更符合统计外推而非战略推理。我们的工作将ICL的机制研究扩展到战略多智能体环境，引入REE作为区分推理与外推的诊断工具，并为探测递归信念任务中LLM推理的边界提供了一个可复用的框架。
英文摘要
In-context learning (ICL) enables large language model (LLM) agents to improve decisions using interaction history, yet it remains unclear whether such improvement reflects refined internal reasoning or mere extrapolation of statistical patterns. To disentangle these mechanisms, we study LLM agents in multi-agent incomplete-information games that require recursive belief reasoning. By constructing a public goods game and manipulating the statistical structure of historical feedback, we evaluate decision quality against a history-independent rational expectations equilibrium (REE) benchmark. Our experiments reveal that when historical statistical patterns are disrupted, the benefits of longer context largely vanish, degrading decision quality to the no-context baseline in a way sharply amplified by stronger strategic interdependence. These results suggest that, in such strategic environments, ICL behavior is more consistent with statistical extrapolation than with strategic reasoning. Our work extends the mechanistic study of ICL to strategic multi-agent settings, introduces REE as a diagnostic tool for distinguishing reasoning from extrapolation, and provides a reusable framework for probing the boundaries of LLM reasoning in recursive belief tasks.
