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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Zeping, Wan, Guancheng, Chen, Keyang, Chen, Yu, Zhao, Yiwen, Torr, Philip, Ye, Guangnan, Yin, Zhenfei, Chai, Hongfeng
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910067101532160
author Li, Zeping
Wan, Guancheng
Chen, Keyang
Chen, Yu
Zhao, Yiwen
Torr, Philip
Ye, Guangnan
Yin, Zhenfei
Chai, Hongfeng
author_facet Li, Zeping
Wan, Guancheng
Chen, Keyang
Chen, Yu
Zhao, Yiwen
Torr, Philip
Ye, Guangnan
Yin, Zhenfei
Chai, Hongfeng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2602_07023
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation
Li, Zeping
Wan, Guancheng
Chen, Keyang
Chen, Yu
Zhao, Yiwen
Torr, Philip
Ye, Guangnan
Yin, Zhenfei
Chai, Hongfeng
Trading and Market Microstructure
Artificial Intelligence
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.
title Behavioral Consistency Validation for LLM Agents: An Analysis of Trading-Style Switching through Stock-Market Simulation
topic Trading and Market Microstructure
Artificial Intelligence
url https://arxiv.org/abs/2602.07023