Dissecting AI Trading: Behavioral Finance and Market Bubbles

TL;DR

This paper explores how AI agents with language-based reasoning form expectations and influence market dynamics, revealing behavioral patterns, equilibrium effects, and the impact of prompt interventions on bubbles.

Contribution

It demonstrates that LLM-based AI agents exhibit human-like trading behaviors and that prompt engineering can causally modify market outcomes in simulated asset markets.

Findings

AI agents show disposition effect and recency bias.

Market dynamics replicate classic experimental results.

Prompt interventions can alter the size of market bubbles.

Abstract

We study how AI agents form expectations and trade in experimental asset markets. Using a simulated open-call auction populated by autonomous Large Language Model (LLM) agents, we document three main findings. First, AI agents exhibit classic behavioral patterns: a pronounced disposition effect and recency-weighted extrapolative beliefs. Second, these individual-level patterns aggregate into equilibrium dynamics that replicate classic experimental findings (Smith et al., 1988), including the predictive power of excess demand for future prices and the positive relationship between disagreement and trading volume. Third, by analyzing the agents' reasoning text through a twenty-mechanism scoring framework, we show that targeted prompt interventions causally amplify or suppress specific behavioral mechanisms, significantly altering the magnitude of market bubbles.