Agent4Rec
🔓 Open SourceGeneral purposeBuild your ownMulti-agent
Overview
Recommender system simulator powered by 1,000 LLM-based generative agents. Each agent embodies distinct social traits and preferences derived from the MovieLens-1M dataset, interacting with personalized movie recommendations through actions like watching, rating, evaluating, and providing feedback in a page-by-page interface.
Details
Agents are initialized with varied behavioral patterns to simulate realistic recommendation scenarios. Supports multiple interaction modes including watching content, rating items, evaluation activities, session exits, and interview-style interactions.