Agent4Rec

Agent4Rec is an open-source recommender system simulator that utilizes 1,000 LLM-empowered generative agents to emulate user interactions with personalized movie recommendations. These agents, initialized from the MovieLens-1M dataset, exhibit diverse social traits and preferences, engaging in realistic interactions such as watching, rating, and evaluating recommended content. The framework explores the potential of LLM-empowered generative agents in simulating human behavior within recommendation environments, offering insights for researchers and developers.