Economic experiments offer a controlled setting for researchers to observe human decision-making and test diverse theories and hypotheses; however, substantial costs and efforts are incurred to gather many individuals as experimental participants. To address this issue, with the development of large language models (LLMs), researchers have recently attempted to develop simulated economic experiments using LLMs-driven agents, called generative agents. If generative agents can replicate human-like decision making in economic experiments, the cost problem of economic experiments can be alleviated. However, despite growing attention, a structured methodology for reliably simulating human behavior using generative agents has not yet emerged. Considering previous research and the current evolutionary stage of LLMs, this study focuses on the reasoning ability of generative agents as a key factor in establishing a framework for this new methodology. A multi-agent simulation, designed to improve the reasoning ability of generative agents through prompting methods, was developed to reproduce the result of an actual economic experiment on the ultimatum game. The results demonstrated that the higher the reasoning ability of the agents, the closer the results were to the theoretical solution, rather than to the real experimental result. The results also suggest that setting the personas of the generative agents may be important for reproducing the results of real economic experiments. These findings provide a foundation for further studies aiming to develop scalable, interpretable, and context-aware LLM-based simulations for experimental economics.