AI代理通过价格波动聚合私有信息，但复杂结构下表现不如人类。
Information Aggregation with AI Agents
- 让AI代理在预测市场中交易，通过价格变化聚合私有信号。
- 简单信息结构下市场准确率高，复杂结构下显著下降。
- 更聪明的AI表现更好，但反馈历史绩效无效。
大型语言模型（AI代理）能否通过交易和观察价格变动来聚合分散的私有信息，并推理他人的知识？我们设计了一项受控实验，让AI代理在获得私有信号后参与预测市场，以最后价格的对数误差衡量信息聚合效果。结果显示，在简单信息结构中，市场能有效聚合信息；但在更复杂的结构中，性能明显下降，表明AI代理在推理他人认知方面可能面临与人类类似的局限性。符合理论预测的是，允许廉价对话、改变市场时长或进行策略提示均未提升市场准确性；初始价格平均影响小，但在极复杂结构中仍起作用。此外，'更聪明'的AI代理在信息聚合和盈利方面表现更优。令人意外的是，提供过去表现反馈并未改善聚合效果。
原文摘要 · Abstract (English)
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, performance deteriorates in the harder structures, suggesting that AI agents may suffer from similar limitations as humans when reasoning about others. Consistent with our theoretical predictions, market accuracy does not improve from allowing cheap talk communication, changing the duration of the market, or strategic prompting; initial price has little average effect but matters in the very hard structure. We also find that "smarter" AI agents perform better at aggregation and are more profitable. Surprisingly, giving them feedback about past performance does not improve aggregation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。