LLM-Agent Interactions on Markets with Information Asymmetries

TL;DR

This study investigates how Large Language Models behave in economic markets with information asymmetries, revealing that institutional design and social preferences significantly influence market outcomes and efficiency.

Contribution

It provides the first simulation-based analysis of LLM agent interactions in credence goods markets, highlighting the importance of social preferences and institutional frameworks.

Findings

LLM agents struggle to cooperate in one-shot markets without liability.

Repeated interactions improve consumer participation but do not eliminate expert fraud.

Market efficiency heavily depends on social preferences and institutional design.

Abstract

As AI agents increasingly act on behalf of human stakeholders in economic settings, understanding their behavior in complex market environments becomes critical. This article examines how Large Language Models coordinate on markets that are characterized by information asymmetries and in which providers of services have incentives to exploit that asymmetry for their own economic gain. To that end, we conduct simulations with GPT-5.1 agents in credence goods markets, manipulating the institutional framework (free market, verifiability, liability), LLM agent's social preferences (default, self-interested, inequity-averse, efficiency-loving), and reputation mechanisms across one-shot and repeated 16-round interactions. In one-shot settings, LLM agents largely fail to establish cooperation, with markets breaking down except under liability rules or when experts have efficiency-loving preferences. Repeated interactions solve consumer participation through competitive price reduction, but expert fraud remains entrenched absent explicit other-regarding preferences. LLM consumers focus narrowly on price levels rather than understanding strategic incentives embedded in markups, making them vulnerable to exploitation. Compared to human experiments, LLM markets exhibit substantially higher consumer participation but much greater market concentration, lower prices, and more polarized fraud patterns. The effect of institutions like verifiability and reputation is also much more ambiguous. Surplus shifts dramatically toward consumers under social-preference objectives. These findings suggest that institutional design for AI agent markets requires fundamentally different approaches than those effective for human actors, with social preference alignment emerging as the primary determinant of market efficiency.