Paper: arXiv 2502.15800
Authors: Thomas Henning, Siddhartha M. Ojha, Ross Spoon, Jiatong Han, Colin F. Camerer
Abstract
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.
Complexity vs Empirical Score
- Math Complexity: 3.5/10
- Empirical Rigor: 7.0/10
- Quadrant: Street Traders — empirical and applied, lower math complexity
Why this score: The paper relies on a well-defined experimental design with clear statistical metrics (MSE, correlation) and visualizations of market behavior, indicating moderate empirical rigor, but its mathematical content is relatively light, focusing on behavioral comparisons rather than dense theoretical derivations.
Research Flowchart
flowchart TD RQ["Research Goal<br>Do LLM agents replicate<br>human market trading<br>and bubble formation?"] --> I["Inputs<br>Experimental Finance Design<br>(Classic Bubble/Crash Paradigm)"] I --> M["Methodology<br>Agent-Based Modeling<br>LLM Agents as Traders"] M --> MP["Market Scenarios<br>1. Single-Model Markets<br>2. Mixed-Model Battle Royale"] MP --> CP["Computational Process<br>Simulated Trading Sessions<br>Asset priced near<br>fundamental value<br>vs. Human trading data"] CP --> F["Key Findings<br>1. LLMs: 'Textbook-Rational'<br>2. Muted Bubble Formation<br>3. Low Strategy Variance<br>4. Do NOT replicate<br>human market dynamics"] F --> O["Outcome<br>LLM-only data is insufficient<br>for replicating<br>key human behavioral features"]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes to compare Large Language Models with human traders in a classic experimental finance paradigm to assess their ability to replicate human market dynamics.
Source sentence
In this study, we compare Large Language Models (LLMs) with human traders in a classic experimental-finance paradigm where prices are determined endogenously.
Assumes 6
- The asset has a known constant fundamental value. market
Source sentence
We adapt an established trading design, where traders buy and sell a risky asset with a known fundamental value
- Dividends are drawn i.i.d. from a Bernoulli distribution over {0.4, 1.0} with equal probability. data
Source sentence
In each period, a unit of stock pays a stochastic dividend drawn i.i.d. from a Bernoulli distribution over {0.4, 1.0}, with equal probability.
- Cash holdings earn a constant risk‑free return. market
Source sentence
Cash holdings earn a constant risk-free return of…
- Human participants receive instructions that mirror the LLM prompts. execution
Source sentence
The human participants were given instructions that mirror the LLM prompts
Show 2 more
- Risk‑elicitation tasks are orthogonal to trading and do not affect outcomes. other
Source sentence
The task was exogenous: lottery choices did not affect cash balances, inventory constraints, or market clearing.
- LLM agents are prompted after each round to describe their strategy, enabling chain‑of‑thought reasoning. model
Source sentence
After each round, LLM agents were prompted to provide details of the strategy they used to drive their trading behavior.
Data
- Human participant data synthetic public
Source sentence
e participants recruited through prolific.com.
- LLM market simulation runs synthetic unknown
Source sentence
We run homogeneous (mono‑agent) markets with single‑model LLM agents and heterogeneous “Battle Royale” markets with multiple LLM models.
Costs
Not modeled
Finds 5
- Claude‑3.5‑Sonnet and GPT‑4o achieve the lowest MSEs (≈0.5‑0.8) and near‑zero correlation with human price paths, keeping prices close to fundamentals. performance
Source sentence
Claude-3.5 Sonnet and GPT-4o yield the lowest MSEs and nearly zero correlation with human price paths, keeping prices close to fundamentals
- LLM agents generally price the asset near its fundamental value, showing “textbook‑rational” behavior and only muted bubble formation. performance
Source sentence
LLM‑agents typically converge on prices near the fundamental value, thereby exhibiting more “textbook-rational” behavior than human subjects.
- LLM markets display lower portfolio‑value variance than human markets, indicating less strategic heterogeneity. statistical
Source sentence
Both also show low portfolio variance, suggesting consistent strategies across instances.
- All AI models outperform human forecasters; human one‑round forecast error ≈1.67 versus AI errors ranging from 0.00 to 0.14. predictive-accuracy
Source sentence
Thus, all AI models outperform human forecasters in terms of forecast accuracy.
- Adding risk‑elicitation lotteries does not materially change LLM trading outcomes relative to the baseline. negative
Source sentence
Adding risk‑elicitation did not materially change outcomes relative to the baseline per model
Checked by others
Supported by
- Financial Stability Implications of Generative AI: Taming the Animal Spirits
Compare the findings
This paper: LLM agents generally price the asset near its fundamental value, showing “textbook‑rational” behavior and only muted bubble formation.
That paper: AI agents exhibit less herd behavior than human financial professionals, suggesting a potential reduction in asset‑price bubbles.
- What Does ChatGPT Make of Historical Stock Returns? Extrapolation and Miscalibration in LLM Stock Return Forecasts
Compare the findings
This paper: All AI models outperform human forecasters; human one‑round forecast error ≈1.67 versus AI errors ranging from 0.00 to 0.14.
That paper: LLM forecasts are considerably better calibrated than human forecasts, indicating improved risk assessment.
Contradicted by
- Machine Spirits: Speculation and Adaptation of LLM Agents in Asset Markets
Compare the findings
This paper: LLM agents generally price the asset near its fundamental value, showing “textbook‑rational” behavior and only muted bubble formation.
That paper: Some LLMs form price bubbles that overprice the asset up to 14.9 times its fundamental price, and these bubbles are almost always speculative.
- Can Large Language Models Trade? Testing Financial Theories with LLM Agents in Market Simulations
Compare the findings
This paper: LLM agents generally price the asset near its fundamental value, showing “textbook‑rational” behavior and only muted bubble formation.
That paper: Interactions among LLM agents generate realistic market dynamics, including price bubbles and corrections, highlighting both capabilities and potential systemic risks.
4 papers in the archive : Shared Models, Selective Trading, and Order Flow ; Machine Spirits: Speculation and Adaptation of LLM Agents in …
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (83)
- Price bubbles with discounting: A web-based classroom experiment (2009) — link
- Algorithm aversion: People erroneously avoid algorithms after seeing them err (2015) — link
- A Turing test of whether AI chatbots are behaviorally similar to humans (2024) — link
- Artificial intelligence and its implications for income distribution and market structure (2020) — link
- Multi-agent reinforcement learning in sequential social dilemmas (2017)
- Large language models in finance: Analyzing sentiment and predicting market trends (2023) — link
- Machine behavior (2019) — link
- Bubbles, crashes, and endogenous expectations in experimental spot asset markets (1988) — link
and 75 more
- What lies beneath: The linguistic traces of deception in online dating profiles (2012) — link
- Chain of thought prompting elicits reasoning in large language models (2022) — link
- Can large language models trade? Assessing AI behavior in financial markets (2022) — link
- Can Large Language Models beat wall street? Evaluating GPT-4’s impact on financial decision-making with MarketSenseAI (2024) — link
- FinRobot: AI Agent for Equity Research and Valuation with Large Language Models — → 2411.08804
- Algorithmic Collusion by Large Language Models (2024) — link
- Strategic Collusion of LLM Agents: Market Division in Multi-Commodity Competitions — → 2410.00031
- GPT-4 Technical Report (2023) — link
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (2022) — link
- Chain-of-Thought Prompting Elicits Reasoning in Large Language Models (2023) — link
- Iterative Refinement with Self-Feedback (2023) — link
- Language Models are Few-Shot Learners (2020) — link
- Playing Games with GPT: What Can We Learn About a Large Language Model from Canonical Strategic Games? (2024) — link
- Playing Repeated Games with Large Language Models (2023) — link
- Overconfidence and Bubbles in Experimental Asset Markets (2016) — link
- Measuring Massive Multitask Language Understanding (2021) — link
- Training Verifiers to Solve Math Word Problems (2021) — link
- Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena (2023) — link
- Price Bubbles, Gender, and Expectations in Experimental Asset Markets (2017) — link
- Can LLMs Mimic Human-Like Mental Accounting and Behavioral Biases? (2024) — link
- Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus? (2023) — link
- Do Large Language Models Reason Like Us? (2024) — link
- Algorithm of Call Auction Price (2010) — link
- Dynamically optimized sequential experimentation (DOSE) for estimating economic preference parameters (2024)
- oTree—An open-source platform for laboratory, online, and field experiments (2016) — link
- Price bubbles in asset market experiments with a flat fundamental value (2005)
- Irrational exuberance and neural crash warning signals during endogenous experimental market bubbles (2014) — link
- Gemini 1.5: Unlocking multimodal understanding across millions of tokens (2024) — link
- Mistral Large (24.11) (2024)
- Grok-2 Beta Release (2024)
- GPT-4o System Card (2024)
- Introducing Claude 3.5 Sonnet (2024)
- OpenAI API (2025) — link
- Latent dirichlet allocation (2003)
- Software Framework for Topic Modelling with Large Corpora (2010)
- Natural language processing with Python: analyzing text with the natural language toolkit (2009)
- Thumbs up? Sentiment classification using machine learning techniques (2002)
- Decision-making behavior evaluation framework for LLMs under uncertain context (2024)
- Comparative analysis of LLM-based market prediction and human expertise with sentiment analysis and machine learning integration (2024)
- K-Level Reasoning: Establishing Higher Order Beliefs in Large Language Models for Strategic Reasoning (2024) — link
- LLM Knows Geometry Better Than Algebra: Numerical Understanding of LLM-based Agents in a Trading Arena — → 2502.17967
- TradingAgents: Multi-agents LLM Financial Trading Framework — → 2412.20138
- A Reflective LLM\textendash Based Agent to Guide Zero\textendash Shot Cryptocurrency Trading — → 2407.09546
- FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design — → 2311.13743
- Pretrained LLM Adapted with LoRA as a Decision Transformer for Offline RL in Quantitative Trading — → 2411.17900
- LLM-Based Routing in Mixture of Experts: A Novel Framework for Trading — → 2501.09636
- TradExpert: Revolutionizing Trading with Mixture of Expert LLMs — → 2411.00782
- Stock Price Prediction with LLM-Guided Market Movement Signals and Transformer Model (2025)
- LLM-Augmented Linear Transformer–CNN for Enhanced Stock Price Prediction (2025)
- HedgeAgents: A Balanced-Aware Multi-Agent Financial Trading System — → 2502.13165
- FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making (2024)
- A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist — → 2402.18485
- Temporal Data Meets LLM–Explainable Financial Time Series Forecasting — → 2306.11025
- Large Language Model Driven Technical Analysis: Enhancing Predictive Accuracy and Interpretability in Stock Trading (2025)
- Can LLM-based Financial Investing Strategies Outperform the Market in Long Run? — → 2505.07078
- FinRL-DeepSeek: LLM-Infused Risk-Sensitive Reinforcement Learning for Trading Agents — → 2502.07393
- When AI Meets Finance (StockAgent): Large Language Model-Based Stock Trading in Simulated Real-World Environments — → 2407.18957
- Can Large Language Models Effectively Process and Execute Financial Trading Instructions? (2024) — link
- When AI Meets Finance (StockAgent): Large Language Model-Based Stock Trading in Simulated Real-World Environments — → 2407.18957
- Enhancing Automated Trading with Sentiment Analysis: Leveraging Large Language Models for Stock Market Predictions (2025)
- What Teaches Robots to Walk, Teaches Them to Trade too–Regime Adaptive Execution using Informed Data and LLMs — → 2406.15508
- Stock Price Trend Prediction Using Emotion Analysis of Financial Headlines with Distilled LLM Model (2024)
- Financial LLM for Stock Price Analysis and Investment Recommendation (2025)
- A Multi-Agent System Based on LLM for Trading Financial Assets (2024)
- Predictive Power of LLMs in Financial Markets — → 2411.16569
- Bubbles, Crashes , and Endogenous Expectations in Experimental Spot Asset Markets (1988) — link
- Empirical Asset Pricing with Large Language Model Agents (2024) — link
- Revolutionizing Finance with LLMs: An Overview of Applications and Insights (2024) — link
- Large Language Models and Financial Market Sentiment (2023) — link
- Sentiment Trading with Large Language Models — → 2412.19245
- Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of Large Language Models — → 2306.12659
- Mental accounting and consumer choice (1985)
- Prospect theory: An analysis of decision under risk (2013)
- Can Generative AI agents behave like humans? Evidence from laboratory market experiments — link
- Can AI Replace Human Subjects? A Large-Scale Replication of Psychological Experiments with LLMs — link
20 of 83 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.