This website uses cookies.

By clicking the "Accept" button or continuing to browse our site, you agree to first-party and session-only cookies being stored on your device to enhance site navigation and analyze site performance and traffic. For more information on our use of cookies, please see our Privacy Policy.

  1. Home
  2. ASSA Annual Meeting
  3. 2026
  4. Program
  5. Large Language Models in Experimental Economics
« Back to Results

Large Language Models in Experimental Economics

Paper Session

Monday, Jan. 5, 2026 10:15 AM - 12:15 PM (EST)

Philadelphia Marriott Downtown, Room 411
Hosted By: Economic Science Association
  • Chair: Colin Camerer, California Institute of Technology

LLM Trading: Analysis of LLM Agent Behaviour in Experimental Asset Markets

Thomas Henning
,
California Institute of Technology
Siddhartha Ojha
,
California Institute of Technology
Ross Spoon
,
Virginia Tech
Jiatong Han
,
California Institute of Technology
Colin Camerer
,
California Institute of Technology

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.

AI Agents Can Enable Superior Market Designs

Ben Manning
,
Massachusetts Institute of Technology
Gili Rusak
,
Harvard University
John Horton
,
Massachusetts Institute of Technology

Abstract

Many theoretically appealing market designs are under-utilized because they demand preference data that humans find costly to provide. This paper demonstrates how large language models (LLMs) can effectively elicit such data from natural language descriptions. In our experiment, human subjects provide free-text descriptions of their tastes over potential roles they could be assigned. An LLM converts these descriptions into cardinal utilities that capture participants’ preferences. We use these utilities and participants’ stated preferences to facilitate three allocation mechanisms---random serial dictatorship, Hylland-Zeckhauser, and a conventional job application type game. A follow-up experiment confirms that participants themselves prefer LLM-generated matches over simpler alternatives under high congestion. These findings suggest that LLM-proxied preference elicitation can enable superior market designs where they would otherwise be impractical to implement.

LLMs Can Model Non-WEIRD Populations: Experiments with Synthetic Cultural Agents

Monica Capra
,
Claremont Graduate University
Augusto Gonzalez-Bonorino
,
Pomona College
Emilio Pantoja
,
Pitzer College

Abstract

Despite its importance, studying economic behavior across diverse, non-WEIRD (Western, Educated, Industrialized, Rich, and Democratic) populations presents significant challenges. We address this issue by introducing a novel methodology that uses Large Language Models (LLMs) to create synthetic cultural agents (SCAs) representing these populations. We subject these SCAs to classic behavioral experiments, including the dictator and ultimatum games. Our results demonstrate substantial cross-cultural variability in experimental behavior. Notably, for populations with available data, SCAs’ behaviors qualitatively resemble those of real human subjects. For unstudied populations, our method can generate novel, testable hypotheses about economic behavior. By integrating AI into experimental economics, this approach offers a proofof-concept for an effective and ethical method to do exploratory analysis, pilot experiments, and refine protocols for hard-to-reach populations. Our study provides a new tool for cross-cultural economic studies and highlights the potential of LLMs to advance experimental and behavioral research.

An Application of Automatic Prompt Optimization: Experimental Tests of Framing Effects

Zhenlin Kang
,
California Institute of Technology
Alex Rolfness
,
California Institute of Technology

Abstract

We use LLM as an “instruction searching” tool. In this paper, we apply the automatic prompt optimization methods to improve the experimental instructions in stag hunt games in a way that systematically induces more coordination on payoff-dominant equilibrium play in LLM simulations. We then test whether the framing effects predicted by LLMs carry over to human subjects in behavioral experiments.

Discussant(s)
Colin Camerer
,
California Institute of Technology
Colin Camerer
,
California Institute of Technology
Colin Camerer
,
California Institute of Technology
Colin Camerer
,
California Institute of Technology
JEL Classifications
  • D9 - Micro-Based Behavioral Economics
  • C6 - Mathematical Methods; Programming Models; Mathematical and Simulation Modeling