Agent4Rec
Visit WebsiteDIY/Build Your Own
Open Source
A simulator utilizing 1,000 LLM-empowered generative agents for personalized movie recommendations.
About
Agent4Rec is a recommender system simulator that employs 1,000 Large Language Model (LLM)-empowered generative agents. These agents are initialized from the MovieLens-1M dataset, embodying varied social traits and preferences. Each agent interacts with personalized movie recommendations in a page-by-page manner and undertakes various actions such as watching, rating, evaluating, exiting, and interviewing. The simulator aims to explore the potential of LLM-empowered generative agents in simulating the behavior of genuine, independent humans in recommendation environments.
Features
- Simulation of 1,000 generative agents with diverse social traits.
- Initialization using the MovieLens-1M dataset.
- Agents perform actions like watching, rating, and evaluating movies.
- Page-by-page interaction with personalized recommendations.
- Open-source platform encouraging community collaboration.
Tags
Recommender Systems
Generative Agents
Simulation