Artificial Institutions: How Institutional Design Shapes LLM Simulations

Abstract

Artificial societies built from large language model (LLM) agents are becoming a practical research tool in economics, political science, sociology, and computer science. Most attention has focused on the properties of the agents: their prompts, personas, memory, reasoning, and similarity to human subjects. This paper argues that the institutional architecture of a simulation is equally important. I demonstrate the point in a small repeated induced-value market experiment. The same LLM agents face the same private values, costs, history, and payoff-framed instructions, while only the rules of exchange vary across five standard market institutions: a call market, posted-offer market, posted-bid market, continuous double auction, and bilateral bargaining. Outcomes differ sharply. Call markets realize 88.6% of efficient surplus; posted-offer and posted-bid markets realize about 66%; continuous double auctions realize 71.5%; and bilateral bargaining realizes 56.4%. Institutions also change trade quantities, price distance from competitive equilibrium, and the division of surplus between buyers and sellers. These results show that even minimal institutional changes can generate qualitatively different artificial social outcomes.