Paper: arXiv 2510.01451

Authors: Anne Lundgaard Hansen, Seung Jung Lee

Abstract

This paper investigates the impact of the adoption of generative AI on financial stability. We conduct laboratory-style experiments using large language models to replicate classic studies on herd behavior in trading decisions. Our results show that AI agents make more rational decisions than humans, relying predominantly on private information over market trends. Increased reliance on AI-powered trading advice could therefore potentially lead to fewer asset price bubbles arising from animal spirits that trade by following the herd. However, exploring variations in the experimental settings reveals that AI agents can be induced to herd optimally when explicitly guided to make profit-maximizing decisions. While optimal herding improves market discipline, this behavior still carries potential implications for financial stability. In other experimental variations, we show that AI agents are not purely algorithmic, but have inherited some elements of human conditioning and bias.

Complexity vs Empirical Score

  • Math Complexity: 3.0/10
  • Empirical Rigor: 6.5/10
  • Quadrant: Street Traders — practical and empirical, lighter on theory

Why this score: This paper presents a novel approach by utilizing LLMs in a laboratory agent-based framework to replicate classic behavioral market micro-structure experiments on herding and financial stability. While the formal mathematical depth is low, the experimental methodology and statistical comparisons against existing human benchmarks are well-structured and clear.

Research Flowchart

  flowchart TD
    A[Research Goal: Assess GenAI Impact on Financial Stability & Herd Behavior] --> B[Methodology: LLM Agent-Based Laboratory Experiments]
    B --> C[Inputs: Classic Trading Decision Frameworks & Private Info Signals]
    C --> D[Simulations: Test Baseline AI Trading vs. Profit-Maximizing Explicit Prompts]
    D --> E[Key Outcome 1: Baseline AI relies on private info, reducing irrational bubbles]
    D --> F[Key Outcome 2: Profit prompts induce optimal herding; human-like biases persist]