A study published in *Scientific Reports* found that agreeableness is the dominant factor promoting cooperation in large language models, while other personality traits had a limited impact. Researchers Mizuki Sakai of Shizuoka University and colleagues examined the relationship between personality traits and cooperative behavior in three OpenAI LLMs—GPT-3.5-turbo, GPT-4o, and GPT-5—using the Big Five Personality Traits framework. The study was conducted in three stages: first measuring basic personality scores using items from the Big Five Inventory (BFI-44); then having the LLMs play repeated Prisoner’s Dilemma games without any personality prompts; and finally comparing that to a condition where the measured personality traits were explicitly provided.