What question did this study set out to answer?

This research examines if Large Language Models can replicate human behaviors in economic markets.

December 21, 2025Open Access

Can Generative AI agents behave like humans? Evidence from laboratory market experiments

View Full Paper

Ask AI

Bookmark

This research examines if Large Language Models can replicate human behaviors in economic markets.
Conducted market experiments with LLM agents influencing each other's decisions.
Analyzed feedback loops between LLMs and the resulting market dynamics observed in labs.
Evaluated LLMs' performance against human participants' behavior.
LLMs showed bounded rationality akin to human behaviors in market scenarios.
Found that LLMs replicate general trends but lack behavioral heterogeneity compared to humans.
Demonstrated that limited context and high variability improved LLMs' market simulations.

No takes yet. Share an insight, caveat, or question.

Laboratory experiments reveal LLMs exhibit bounded rationality like humans, indicating potential for simulating market behavior.

Rio-Chanona et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark