Dataset for: Effects of Personality Steering on Cooperative Behavior in Large Language Model Agents

This dataset contains the experimental data used in the study "Effects of Personality Steering on Cooperative Behavior in Large Language Model Agents."https://arxiv.org/abs/2601.05302 The dataset includes results from repeated Prisoner's Dilemma games conducted with multiple large language models (GPT-3.5-turbo, GPT-4o, and GPT-5). Agents were assigned personality traits based on the Big Five framework, and their cooperative behavior was evaluated under both baseline and personality-informed conditions. The dataset is provided to ensure transparency and reproducibility of the reported results.