Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation

2026-02-02

AI Summary

This study investigates whether the trading behavior of large language model (LLM) agents in a simulated stock market aligns with behavioral finance theories, with a particular focus on the consistency of their strategy switching. Over a one-year simulation, agents traded based on daily price and volume data and dynamically adjusted their strategies every ten trading days according to four behavioral drivers: loss aversion, herding, wealth dispersion, and price misalignment. Innovatively, these drivers were embedded as persistent “personality traits” within the agents. Four alignment metrics were designed to evaluate the coherence between the agents’ strategy shifts and theoretical expectations. Empirical results, derived through prompt engineering and Mann-Whitney U tests, indicate that current LLM agents only partially conform to behavioral finance predictions, revealing limitations in modeling behavioral consistency and highlighting avenues for improvement.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Game Theory and Economic Paradigms: Behavioral Game Theory

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recent works have increasingly applied Large Language Models (LLMs) as agents in financial stock market simulations to test if micro-level behaviors aggregate into macro-level phenomena. However, a crucial question arises: Do LLM agents'behaviors align with real market participants? This alignment is key to the validity of simulation results. To explore this, we select a financial stock market scenario to test behavioral consistency. Investors are typically classified as fundamental or technical traders, but most simulations fix strategies at initialization, failing to reflect real-world trading dynamics. In this work, we assess whether agents'strategy switching aligns with financial theory, providing a framework for this evaluation. We operationalize four behavioral-finance drivers-loss aversion, herding, wealth differentiation, and price misalignment-as personality traits set via prompting and stored long-term. In year-long simulations, agents process daily price-volume data, trade under a designated style, and reassess their strategy every 10 trading days. We introduce four alignment metrics and use Mann-Whitney U tests to compare agents'style-switching behavior with financial theory. Our results show that recent LLMs'switching behavior is only partially consistent with behavioral-finance theories, highlighting the need for further refinement in aligning agent behavior with financial theory.

Problem

• behavioral consistency
• LLM agents
• trading-style switching
• stock-market simulation
• behavioral finance

Innovation

• behavioral consistency
• LLM agents
• trading-style switching
• stock-market simulation
• behavioral finance