2025/07/01 by Siting Estee Lu · 1 voice
Social Sciences · Decision Sciences · #Experimental Behavioral Economics Studies #Game Theory and Applications #Media Influence and Politics
paper · doi:10.18559/ebr.2025.2.2182
openalex publication_date 2025/07/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/05/21
The growing adoption of large language models (LLMs) presents potential for deeper understanding of human behaviours within game theory frameworks. This paper examines strategic interactions among multiple types of LLM-based agents in a classical beauty contest game. LLM-based agents demonstrate varying depth of reasoning that fall within a range of level-0 to 1, which are lower than experimental results conducted with human subjects in previous literature, but they display similar convergence pattern towards Nash Equilibrium choice in repeated setting. Through simulations that varies the group composition of agent types, I found that environment with lower strategic uncertainty enhances convergence for LLM-based agents, and environments with mixed strategic types accelerate convergence for all. Results with simulated agents not only convey insights on potential human behaviours in competitive setting, they also offer valuable understanding of strategic interactions among algorithms.