Information Aggregation with AI Agents

Can Large Language Models (AI agents) aggregate dispersed private information through trading and reason about the knowledge of others by observing price move ments? 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 ag gregating information in the easy information structures, increasing the complexity has a significant negative impact, suggesting that AI agents may suffer from similar limitations as humans when reasoning about others. Consistent with our theoretical predictions, information aggregation remains unaffected by allowing cheap talk commu nication, 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 are more profitable. Surprisingly, giving them feedback about past performance has no impact on aggregation.