LLM Agents Do Not Replicate Human Market Traders: Evidence From Experimental Finance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Henning, Thomas, Ojha, Siddhartha M., Spoon, Ross, Han, Jiatong, Camerer, Colin F.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914087193018368
author Henning, Thomas
Ojha, Siddhartha M.
Spoon, Ross
Han, Jiatong
Camerer, Colin F.
author_facet Henning, Thomas
Ojha, Siddhartha M.
Spoon, Ross
Han, Jiatong
Camerer, Colin F.
contents This paper explores how Large Language Models (LLMs) behave in a classic experimental finance paradigm widely known for eliciting bubbles and crashes in human participants. We adapt an established trading design, where traders buy and sell a risky asset with a known fundamental value, and introduce several LLM-based agents, both in single-model markets (all traders are instances of the same LLM) and in mixed-model "battle royale" settings (multiple LLMs competing in the same market). Our findings reveal that LLMs generally exhibit a "textbook-rational" approach, pricing the asset near its fundamental value, and show only a muted tendency toward bubble formation. Further analyses indicate that LLM-based agents display less trading strategy variance in contrast to humans. Taken together, these results highlight the risk of relying on LLM-only data to replicate human-driven market phenomena, as key behavioral features, such as large emergent bubbles, were not robustly reproduced. While LLMs clearly possess the capacity for strategic decision-making, their relative consistency and rationality suggest that they do not accurately mimic human market dynamics.
format Preprint
id arxiv_https___arxiv_org_abs_2502_15800
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM Agents Do Not Replicate Human Market Traders: Evidence From Experimental Finance
Henning, Thomas
Ojha, Siddhartha M.
Spoon, Ross
Han, Jiatong
Camerer, Colin F.
Trading and Market Microstructure
This paper explores how Large Language Models (LLMs) behave in a classic experimental finance paradigm widely known for eliciting bubbles and crashes in human participants. We adapt an established trading design, where traders buy and sell a risky asset with a known fundamental value, and introduce several LLM-based agents, both in single-model markets (all traders are instances of the same LLM) and in mixed-model "battle royale" settings (multiple LLMs competing in the same market). Our findings reveal that LLMs generally exhibit a "textbook-rational" approach, pricing the asset near its fundamental value, and show only a muted tendency toward bubble formation. Further analyses indicate that LLM-based agents display less trading strategy variance in contrast to humans. Taken together, these results highlight the risk of relying on LLM-only data to replicate human-driven market phenomena, as key behavioral features, such as large emergent bubbles, were not robustly reproduced. While LLMs clearly possess the capacity for strategic decision-making, their relative consistency and rationality suggest that they do not accurately mimic human market dynamics.
title LLM Agents Do Not Replicate Human Market Traders: Evidence From Experimental Finance
topic Trading and Market Microstructure
url https://arxiv.org/abs/2502.15800