This study constructs an artificial market simulation incorporating large language models (LLMs) as decision-making agents and evaluates their ability to reproduce market stylized facts. LLMs have been widely applied across various domains, including finance, where they can process texts and outputs in a manner similar to humans. Through training on extensive corpora, these models are capable of generating data that accords with average thought patterns. In this research, we propose utilizing LLMs for decision-making processes in artificial market simulations. Previous research has employed simulations that manually constructed traders’ algorithms incorporating fundamental, chartist (trend), and noise factors. However, our simulation design replaces the fundamental and chartist factors with LLM decision-making, while retaining noise factors. For our LLM agent prompts, we created eight prompt patterns, which include three optional elements ( \(2^3\) patterns): prospect theory prompt, position prompt, and fundamental prompt. We then analyzed the performance effects of each optional prompt. Our experimental results demonstrate that appropriate prompt design can successfully reproduce market stylized facts. Notably, all three prompt elements–fundamentals, position, and prospect theory prompts–were necessary to reproduce the stylized facts of financial markets. It means that effective prompt engineering plays a crucial role in enhancing the realism of artificial markets. This study not only showcases the potential applications of LLMs in financial market research but also provides important insights into actual LLM usages for finance.