Problem
Research questions and friction points this paper is trying to address.
In-context learning
Multi-agent decision-making
Recursive reasoning
Statistical extrapolation
Incomplete-information games
Recursive Reasoning or Statistical Extrapolation? In-Context Learning in Multi-Agent Interdependent Decision-Making
🤖 AI Summary
研究通过公共物品游戏探讨了大语言模型在多智能体决策中基于上下文学习的机制，揭示其更多依赖统计外推而非递归推理。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
In-Context Learning
Recursive Belief Reasoning
Rational Expectations Equilibrium
Statistical Extrapolation
🔎 Similar Papers
No similar papers found.
