IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2510.25743.html
   My bibliography  Save this paper

Agentic Economic Modeling

Author

Listed:
  • Bohan Zhang
  • Jiaxuan Li
  • Ali Hortac{c}su
  • Xiaoyang Ye
  • Victor Chernozhukov
  • Angelo Ni
  • Edward Huang

Abstract

We introduce Agentic Economic Modeling (AEM), a framework that aligns synthetic LLM choices with small-sample human evidence for reliable econometric inference. AEM first generates task-conditioned synthetic choices via LLMs, then learns a bias-correction mapping from task features and raw LLM choices to human-aligned choices, upon which standard econometric estimators perform inference to recover demand elasticities and treatment effects.We validate AEM in two experiments. In a large scale conjoint study with millions of observations, using only 10% of the original data to fit the correction model lowers the error of the demand-parameter estimates, while uncorrected LLM choices even increase the errors. In a regional field experiment, a mixture model calibrated on 10% of geographic regions estimates an out-of-domain treatment effect of -65\pm10 bps, closely matching the full human experiment (-60\pm8 bps).Under time-wise extrapolation, training with only day-one human data yields -24 bps (95% CI: [-26, -22], p

Suggested Citation

  • Bohan Zhang & Jiaxuan Li & Ali Hortac{c}su & Xiaoyang Ye & Victor Chernozhukov & Angelo Ni & Edward Huang, 2025. "Agentic Economic Modeling," Papers 2510.25743, arXiv.org.
    • Handle: RePEc:arx:papers:2510.25743
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2510.25743
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Yiting Chen & Tracy Xiao Liu & You Shan & Songfa Zhong, 2023. "The emergence of economic rationality of GPT," Proceedings of the National Academy of Sciences, Proceedings of the National Academy of Sciences, vol. 120(51), pages 2316205120-, December.
    2. 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.
    3. Ali Goli & Amandeep Singh, 2024. "Frontiers: Can Large Language Models Capture Human Preferences?," Marketing Science, INFORMS, vol. 43(4), pages 709-722, July.
    4. Jeongbin Kim & Matthew Kovach & Kyu-Min Lee & Euncheol Shin & Hector Tzavellas, 2024. "Learning to be Homo Economicus: Can an LLM Learn Preferences from Choice," Papers 2401.07345, arXiv.org.
    5. McFadden, Daniel, 1980. "Econometric Models for Probabilistic Choice among Products," The Journal of Business, University of Chicago Press, vol. 53(3), pages 13-29, July.
    6. Alex Lyman & Bryce Hepner & Lisa P. Argyle & Ethan C. Busby & Joshua R. Gubler & David Wingate, 2025. "Balancing Large Language Model Alignment and Algorithmic Fidelity in Social Science Research," Sociological Methods & Research, , vol. 54(3), pages 1110-1155, August.
    7. Gary Charness & Brian Jabarian & John A. List, 2025. "The next generation of experimental research with LLMs," Nature Human Behaviour, Nature, vol. 9(5), pages 833-835, May.
    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. Shu Wang & Zijun Yao & Shuhuai Zhang & Jianuo Gai & Tracy Xiao Liu & Songfa Zhong, 2025. "When Experimental Economics Meets Large Language Models: Evidence-based Tactics," Papers 2505.21371, arXiv.org, revised Jul 2025.
    2. Matthew O. Jackson & Qiaozhu Me & Stephanie W. Wang & Yutong Xie & Walter Yuan & Seth Benzell & Erik Brynjolfsson & Colin F. Camerer & James Evans & Brian Jabarian & Jon Kleinberg & Juanjuan Meng & Se, 2025. "AI Behavioral Science," Papers 2509.13323, arXiv.org.
    3. Tianshi Mu & Pranjal Rawat & John Rust & Chengjun Zhang & Qixuan Zhong, 2025. "Who is More Bayesian: Humans or ChatGPT?," Papers 2504.10636, arXiv.org.
    4. John Rust & Tianshi Mu & Pranjal Rawat & Chengjun Zhang & Qixuan Zhong, 2025. "Who is More Bayesian: Humans or ChatGPT?," Working Papers gueconwpa~25-25-02, Georgetown University, Department of Economics.
    5. Herbert Dawid & Philipp Harting & Hankui Wang & Zhongli Wang & Jiachen Yi, 2025. "Agentic Workflows for Economic Research: Design and Implementation," Papers 2504.09736, arXiv.org.
    6. Qiang Chen & Tianyang Han & Jin Li & Ye Luo & Yuxiao Wu & Xiaowei Zhang & Tuo Zhou, 2025. "Can AI Master Econometrics? Evidence from Econometrics AI Agent on Expert-Level Tasks," Papers 2506.00856, arXiv.org, revised Jun 2025.
    7. Paleti, Rajesh, 2018. "Generalized multinomial probit Model: Accommodating constrained random parameters," Transportation Research Part B: Methodological, Elsevier, vol. 118(C), pages 248-262.
    8. Nguyen-Phuoc, Duy Q. & Currie, Graham & De Gruyter, Chris & Young, William, 2018. "Transit user reactions to major service withdrawal – A behavioural study," Transport Policy, Elsevier, vol. 64(C), pages 29-37.
    9. Iñaki Aldasoro & Ajit Desai, 2025. "Money Talks: AI Agents for Cash Management in Payment Systems," Staff Working Papers 25-35, Bank of Canada.
    10. Jakusch, Sven Thorsten, 2017. "On the applicability of maximum likelihood methods: From experimental to financial data," SAFE Working Paper Series 148, Leibniz Institute for Financial Research SAFE, revised 2017.
    11. Kanchanaroek, Yingluk & Termansen, Mette & Quinn, Claire, 2013. "Property rights regimes in complex fishery management systems: A choice experiment application," Ecological Economics, Elsevier, vol. 93(C), pages 363-373.
    12. Ericka Costa & Dario Montemurro & Diego Giuliani, 2019. "Consumers’ willingness to pay for green cars: a discrete choice analysis in Italy," Environment, Development and Sustainability: A Multidisciplinary Approach to the Theory and Practice of Sustainable Development, Springer, vol. 21(5), pages 2425-2442, October.
    13. Partha Deb & Chenghui Li & Pravin K. Trivedi & David M. Zimmer, 2006. "The effect of managed care on use of health care services: results from two contemporaneous household surveys," Health Economics, John Wiley & Sons, Ltd., vol. 15(7), pages 743-760, July.
    14. Francesco Venturini, 2025. "Generative AI and Income Growth: Early Evidence on Global Data," Gospodarka Narodowa. The Polish Journal of Economics, Warsaw School of Economics, issue 3, pages 31-46.
    15. Daniel McFadden, 2009. "The human side of mechanism design: a tribute to Leo Hurwicz and Jean-Jacque Laffont," Review of Economic Design, Springer;Society for Economic Design, vol. 13(1), pages 77-100, April.
    16. Panu Jalas, 2025. "Discussion about the assumptions of Category Theory approach to agent-based modeling in microeconomics," Papers 2503.14672, arXiv.org.
    17. Fu, Shengfei & Florkowski, Wojciech, 2016. "Polish Household Consumption of Tobacco and Alcohol: A Censored System," 2016 Annual Meeting, February 6-9, 2016, San Antonio, Texas 229795, Southern Agricultural Economics Association.
    18. Johanna Lena Dahlhausen & Cam Rungie & Jutta Roosen, 2018. "Value of labeling credence attributes—common structures and individual preferences," Agricultural Economics, International Association of Agricultural Economists, vol. 49(6), pages 741-751, November.
    19. Pawe{l} Niszczota & Tomasz Grzegorczyk & Alexander Pastukhov, 2025. "People Are Highly Cooperative with Large Language Models, Especially When Communication Is Possible or Following Human Interaction," Papers 2507.18639, arXiv.org.
    20. Kim, GwanSeon & Mark, Tyler, "undated". "Who are Consuming Hemp Products in the U.S.? Evidence from Nielsen Homescan Data," 2018 Annual Meeting, February 2-6, 2018, Jacksonville, Florida 266671, Southern Agricultural Economics Association.

    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:2510.25743. 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.