Can Large Language Models (AI agents) aggregate dispersed private information through trading and reason about the knowledge of others by observing price movements? We conduct a controlled experiment where AI agents trade in a prediction market after receiving private signals, measuring information aggregation by the log error of the last price. We find that although the median market is effective at aggregating information in the easy information structures, increasing the complexity has a significant and negative impact, suggesting that AI agents may suffer from the same limitations as humans when reasoning about others. Consistent with our theoretical predictions, information aggregation remains unaffected by allowing cheap talk communication, changing the duration of the market or initial price, and strategic prompting-thus demonstrating that prediction markets are robust. We establish that "smarter" AI agents perform better at aggregation and they are more profitable. Surprisingly, giving them feedback about past performance makes them worse at aggregation and reduces their profits.

翻译：大型语言模型（AI代理）能否通过交易聚合分散的私有信息，并通过观察价格变动推理他人的知识？我们开展了一项受控实验，让AI代理在接收私有信号后于预测市场中进行交易，通过最后价格的对数误差衡量信息聚合程度。研究发现：虽然中等市场在简单信息结构下能有效聚合信息，但增加复杂度会显著产生负面影响，这表明AI代理在推理他人思维时可能存在与人类相同的局限性。与理论预测一致的是，允许廉价交谈、改变市场持续时间或初始价格、以及策略性提示均未影响信息聚合——这证明了预测市场的鲁棒性。我们证实，"更智能"的AI代理在聚合方面表现更优且盈利更高。令人惊讶的是，向它们提供过往表现反馈反而会削弱聚合能力并降低利润。