IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2511.08604.html

Generative Agents and Expectations: Do LLMs Align with Heterogeneous Agent Models?

Author

Listed:
  • Filippo Gusella
  • Eugenio Vicario

Abstract

Results in the Heterogeneous Agent Model (HAM) literature determine the proportion of fundamentalists and trend followers in the financial market. This proportion varies according to the periods analyzed. In this paper, we use a large language model (LLM) to construct a generative agent (GA) that determines the probability of adopting one of the two strategies based on current information. The probabilities of strategy adoption are compared with those in the HAM literature for the S\&P 500 index between 1990 and 2020. Our findings suggest that the resulting artificial intelligence (AI) expectations align with those reported in the HAM literature. At the same time, extending the analysis to artificial market data helps us to filter the decision-making process of the AI agent. In the artificial market, results confirm the heterogeneity in expectations but reveal systematic asymmetry toward the fundamentalist behavior.

Suggested Citation

  • Filippo Gusella & Eugenio Vicario, 2025. "Generative Agents and Expectations: Do LLMs Align with Heterogeneous Agent Models?," Papers 2511.08604, arXiv.org.
    • Handle: RePEc:arx:papers:2511.08604
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2511.08604
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yao Qu & Jue Wang, 2024. "Performance and biases of Large Language Models in public opinion simulation," Humanities and Social Sciences Communications, Palgrave Macmillan, vol. 11(1), pages 1-13, December.
    2. Day, Richard H. & Huang, Weihong, 1990. "Bulls, bears and market sheep," Journal of Economic Behavior & Organization, Elsevier, vol. 14(3), pages 299-329, December.
    3. Hommes, Cars & in ’t Veld, Daan, 2017. "Booms, busts and behavioural heterogeneity in stock prices," Journal of Economic Dynamics and Control, Elsevier, vol. 80(C), pages 101-124.
    4. Stefan Reitz & Frank Westerhoff, 2007. "Commodity price cycles and heterogeneous speculators: a STAR–GARCH model," Empirical Economics, Springer, vol. 33(2), pages 231-244, September.
    5. Majewski, Adam A. & Ciliberti, Stefano & Bouchaud, Jean-Philippe, 2020. "Co-existence of trend and value in financial markets: Estimating an extended Chiarella model," Journal of Economic Dynamics and Control, Elsevier, vol. 112(C).
    6. Cagno, Daniela Di & Lin, Lihui, 2025. "How do individuals interact with an AI advisor in strategic reasoning? An experimental study in beauty contest," Journal of Economic Behavior & Organization, Elsevier, vol. 237(C).
    7. Bolt, Wilko & Demertzis, Maria & Diks, Cees & Hommes, Cars & Leij, Marco van der, 2019. "Identifying booms and busts in house prices under heterogeneous expectations," Journal of Economic Dynamics and Control, Elsevier, vol. 103(C), pages 234-259.
    8. Delli Gatti, Domenico & Gusella, Filippo & Ricchiuti, Giorgio, 2025. "Endogenous vs exogenous fluctuations: unveiling the impact of heterogeneous expectations," Macroeconomic Dynamics, Cambridge University Press, vol. 29, pages 1-1, January.
    9. Alejandro Lopez-Lira, 2025. "Can Large Language Models Trade? Testing Financial Theories with LLM Agents in Market Simulations," Papers 2504.10789, arXiv.org.
    10. Recchioni, Maria Cristina & Tedeschi, Gabriele & Gallegati, Mauro, 2015. "A calibration procedure for analyzing stock price dynamics in an agent-based framework," Journal of Economic Dynamics and Control, Elsevier, vol. 60(C), pages 1-25.
    11. Giovanni Dosi & Andrea Roventini, 2019. "More is different ... and complex! the case for agent-based macroeconomics," Journal of Evolutionary Economics, Springer, vol. 29(1), pages 1-37, March.
    12. Lux, Thomas, 2018. "Estimation of agent-based models using sequential Monte Carlo methods," Journal of Economic Dynamics and Control, Elsevier, vol. 91(C), pages 391-408.
    13. Goldbaum, David & Zwinkels, Remco C.J., 2014. "An empirical examination of heterogeneity and switching in foreign exchange markets," Journal of Economic Behavior & Organization, Elsevier, vol. 107(PB), pages 667-684.
    14. Adriana Cornea-Madeira & Cars Hommes & Domenico Massaro, 2019. "Behavioral Heterogeneity in U.S. Inflation Dynamics," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 37(2), pages 288-300, April.
    15. Lucas, Robert Jr., 1972. "Expectations and the neutrality of money," Journal of Economic Theory, Elsevier, vol. 4(2), pages 103-124, April.
    16. Anton Korinek, 2023. "Generative AI for Economic Research: Use Cases and Implications for Economists," Journal of Economic Literature, American Economic Association, vol. 61(4), pages 1281-1317, December.
    17. Lux, Thomas, 1995. "Herd Behaviour, Bubbles and Crashes," Economic Journal, Royal Economic Society, vol. 105(431), pages 881-896, July.
    18. Chiarella, Carl & He, Xue-Zhong & Zwinkels, Remco C.J., 2014. "Heterogeneous expectations in asset pricing: Empirical evidence from the S&P500," Journal of Economic Behavior & Organization, Elsevier, vol. 105(C), pages 1-16.
    19. Filippo Gusella & Giorgio Ricchiuti, 2024. "Endogenous cycles in heterogeneous agent models: a state-space approach," Journal of Evolutionary Economics, Springer, vol. 34(4), pages 739-782, December.
    20. Schmitt, Noemi & Westerhoff, Frank, 2021. "Trend followers, contrarians and fundamentalists: Explaining the dynamics of financial markets," Journal of Economic Behavior & Organization, Elsevier, vol. 192(C), pages 117-136.
    21. Chen Gao & Xiaochong Lan & Nian Li & Yuan Yuan & Jingtao Ding & Zhilun Zhou & Fengli Xu & Yong Li, 2024. "Large language models empowered agent-based modeling and simulation: a survey and perspectives," Humanities and Social Sciences Communications, Palgrave Macmillan, vol. 11(1), pages 1-24, December.
    22. Di Francesco, Tommaso & Hommes, Cars, 2025. "Sentiment-driven speculation in financial markets with heterogeneous beliefs: A machine learning approach," Journal of Economic Dynamics and Control, Elsevier, vol. 175(C).
    23. James W. A. Strachan & Dalila Albergo & Giulia Borghini & Oriana Pansardi & Eugenio Scaliti & Saurabh Gupta & Krati Saxena & Alessandro Rufo & Stefano Panzeri & Guido Manzi & Michael S. A. Graziano & , 2024. "Testing theory of mind in large language models and humans," Nature Human Behaviour, Nature, vol. 8(7), pages 1285-1295, July.
    24. Cars Hommes, 2021. "Behavioral and Experimental Macroeconomics and Policy Analysis: A Complex Systems Approach," Journal of Economic Literature, American Economic Association, vol. 59(1), pages 149-219, March.
    25. Lux, Thomas, 2024. "Lack of identification of parameters in a simple behavioral macroeconomic model," Economics Working Papers 2024-02, Christian-Albrechts-University of Kiel, Department of Economics.
    26. Lux, Thomas, 2024. "Lack of identification of parameters in a simple behavioral macroeconomic model," Journal of Economic Dynamics and Control, Elsevier, vol. 168(C).
    27. Schmitt, Noemi, 2021. "Heterogeneous Expectations And Asset Price Dynamics," Macroeconomic Dynamics, Cambridge University Press, vol. 25(6), pages 1538-1568, September.
    28. Milena Tsvetkova & Taha Yasseri & Niccolo Pescetelli & Tobias Werner, 2024. "A new sociology of humans and machines," Nature Human Behaviour, Nature, vol. 8(10), pages 1864-1876, October.
    29. Motoki, Fabio Y.S. & Pinho Neto, Valdemar & Rangel, Victor, 2025. "Assessing political bias and value misalignment in generative artificial intelligence," Journal of Economic Behavior & Organization, Elsevier, vol. 234(C).
    30. Bolt, Wilko & Demertzis, Maria & Diks, Cees & Hommes, Cars & Leij, Marco van der, 2019. "Identifying booms and busts in house prices under heterogeneous expectations," Journal of Economic Dynamics and Control, Elsevier, vol. 103(C), pages 234-259.
    31. Kukacka, Jiri & Sacht, Stephen, 2023. "Estimation of heuristic switching in behavioral macroeconomic models," Journal of Economic Dynamics and Control, Elsevier, vol. 146(C).
    32. Chiarella, Carl & He, Xue-Zhong & Huang, Weihong & Zheng, Huanhuan, 2012. "Estimating behavioural heterogeneity under regime switching," Journal of Economic Behavior & Organization, Elsevier, vol. 83(3), pages 446-460.
    33. R. Maria del Rio-Chanona & Marco Pangallo & Cars Hommes, 2025. "Can Generative AI agents behave like humans? Evidence from laboratory market experiments," Papers 2505.07457, arXiv.org.
    34. John J. Horton, 2023. "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?," NBER Working Papers 31122, National Bureau of Economic Research, Inc.
    35. John J. Horton, 2023. "Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?," Papers 2301.07543, arXiv.org.
    36. Kukacka, Jiri & Barunik, Jozef, 2017. "Estimation of financial agent-based models with simulated maximum likelihood," Journal of Economic Dynamics and Control, Elsevier, vol. 85(C), pages 21-45.
    37. Fama, Eugene F, 1991. "Efficient Capital Markets: II," Journal of Finance, American Finance Association, vol. 46(5), pages 1575-1617, December.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Filippo Gusella & Giorgio Ricchiuti, 2024. "Endogenous cycles in heterogeneous agent models: a state-space approach," Journal of Evolutionary Economics, Springer, vol. 34(4), pages 739-782, December.
    2. Saskia ter Ellen & Willem F. C. Verschoor, 2018. "Heterogeneous Beliefs and Asset Price Dynamics: A Survey of Recent Evidence," Dynamic Modeling and Econometrics in Economics and Finance, in: Fredj Jawadi (ed.), Uncertainty, Expectations and Asset Price Dynamics, pages 53-79, Springer.
    3. Kukacka, Jiri & Barunik, Jozef, 2017. "Estimation of financial agent-based models with simulated maximum likelihood," Journal of Economic Dynamics and Control, Elsevier, vol. 85(C), pages 21-45.
    4. Domenico Delli Gatti & Filippo Gusella & Giorgio Ricchiuti, 2024. "Endogenous vs Exogenous Instability: An Out-of-Sample Comparison," Working Papers - Economics wp2024_05.rdf, Universita' degli Studi di Firenze, Dipartimento di Scienze per l'Economia e l'Impresa.
    5. Filippo Gusella & Giorgio Ricchiuti, 2022. "A State-Space Approach for Time-Series Prediction of an Heterogeneous Agent Model," Working Papers - Economics wp2022_20.rdf, Universita' degli Studi di Firenze, Dipartimento di Scienze per l'Economia e l'Impresa.
    6. ter Ellen, Saskia & Hommes, Cars H. & Zwinkels, Remco C.J., 2021. "Comparing behavioural heterogeneity across asset classes," Journal of Economic Behavior & Organization, Elsevier, vol. 185(C), pages 747-769.
    7. Di Francesco, Tommaso & Hommes, Cars, 2025. "Sentiment-driven speculation in financial markets with heterogeneous beliefs: A machine learning approach," Journal of Economic Dynamics and Control, Elsevier, vol. 175(C).
    8. Filippo Gusella, 2022. "Detecting And Measuring Financial Cycles In Heterogeneous Agents Models: An Empirical Analysis," Advances in Complex Systems (ACS), World Scientific Publishing Co. Pte. Ltd., vol. 25(02n03), pages 1-22, March.
    9. Tubbenhauer, Tobias & Fieberg, Christian & Poddig, Thorsten, 2021. "Multi-agent-based VaR forecasting," Journal of Economic Dynamics and Control, Elsevier, vol. 131(C).
    10. Chen, Zhenxi, 2016. "Regimes dependent speculative trading: Evidence from the United States housing market," FinMaP-Working Papers 66, Collaborative EU Project FinMaP - Financial Distortions and Macroeconomic Performance: Expectations, Constraints and Interaction of Agents.
    11. Piero Mazzarisi & Alessio Muscillo & Claudio Pacati & Paolo Pin, 2024. "The Rise and Fall of Ideas' Popularity," Papers 2411.18541, arXiv.org, revised Nov 2024.
    12. Zhao, Dongxu & Li, Kai, 2022. "Bounded rationality, adaptive behaviour, and asset prices," International Review of Financial Analysis, Elsevier, vol. 80(C).
    13. Filippo Gusella & Giorgio Ricchiuti, 2021. "State Space Model to Detect Cycles in Heterogeneous Agents Models," Working Papers - Economics wp2021_10.rdf, Universita' degli Studi di Firenze, Dipartimento di Scienze per l'Economia e l'Impresa.
    14. Roberto Dieci & Xue-Zhong He, 2018. "Heterogeneous Agent Models in Finance," Research Paper Series 389, Quantitative Finance Research Centre, University of Technology, Sydney.
    15. Zheng, Min & Wang, Hefei & Wang, Chengzhang & Wang, Shouyang, 2017. "Speculative behavior in a housing market: Boom and bust," Economic Modelling, Elsevier, vol. 61(C), pages 50-64.
    16. Guillaume Coqueret, 2016. "Empirical properties of a heterogeneous agent model in large dimensions," Post-Print hal-02088097, HAL.
    17. Xue-Zhong He & Youwei Li, 2017. "The adaptiveness in stock markets: testing the stylized facts in the DAX 30," Journal of Evolutionary Economics, Springer, vol. 27(5), pages 1071-1094, November.
    18. Dieci, Roberto & Schmitt, Noemi & Westerhoff, Frank, 2018. "Interactions between stock, bond and housing markets," Journal of Economic Dynamics and Control, Elsevier, vol. 91(C), pages 43-70.
    19. Schmitt, Noemi & Westerhoff, Frank, 2021. "Trend followers, contrarians and fundamentalists: Explaining the dynamics of financial markets," Journal of Economic Behavior & Organization, Elsevier, vol. 192(C), pages 117-136.
    20. Guillaume Coqueret, 2017. "Empirical properties of a heterogeneous agent model in large dimensions," Post-Print hal-02000726, HAL.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2511.08604. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.