Agentic Economic Modeling

Bohan Zhang, Jiaxuan Li, Ali Horta\c{c}su, Xiaoyang Ye, Victor Chernozhukov, Angelo Ni and Edward Huang

Papers from arXiv.org

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

Date: 2025-10
New Economics Papers: this item is included in nep-ain, nep-ecm and nep-exp
References: Add references at CitEc
Citations:

Downloads: (external link)
http://arxiv.org/pdf/2510.25743 Latest version (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:arx:papers:2510.25743

Access Statistics for this paper

More papers in Papers from arXiv.org
Bibliographic data for series maintained by arXiv administrators ().