Information Aggregation with AI Agents

Spyros Galanis

No 2026_02, Department of Economics Working Papers from Durham University, Department of Economics

Abstract: 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.

Keywords: Information Aggregation; AI agents; Artificial Intelligence; Financial Mar kets; Prediction Markets; Experiments (search for similar items in EconPapers)
JEL-codes: C91 D82 D83 D84 G14 G41 (search for similar items in EconPapers)
Date: 2026-05
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.durham.ac.uk/business/media/durham-uni ... pdfs/EconWP26_02.pdf main text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:dur:durham:2026_02

Access Statistics for this paper

More papers in Department of Economics Working Papers from Durham University, Department of Economics Durham University Business School, Mill Hill Lane, Durham DH1 3LB, England. Contact information at EDIRC.
Bibliographic data for series maintained by Tatiana Damjanovic ().