Agent4Rec
An open-source recommender system simulator utilizing 1,000 LLM-empowered generative agents to emulate user interactions with personalized movie recommendations.
Agent4Rec
An open-source recommender system simulator utilizing 1,000 LLM-empowered generative agents to emulate user interactions with personalized movie recommendations.
Agent4Rec
SKU: agent4rec
Agent4Rec is an innovative recommender system simulator that leverages Large Language Models (LLMs) to create 1,000 generative agents, each initialized from the MovieLens-1M dataset. These agents exhibit diverse social traits and preferences, engaging in realistic interactions with personalized movie recommendations. Actions include watching, rating, evaluating, exiting, and conducting interviews about recommended content. Designed to provide insights into human behavior within recommendation environments, Agent4Rec serves as a valuable tool for researchers and developers aiming to study and enhance recommender systems.
recommender system simulator
LLM generative agents
user behavior simulation
MovieLens dataset
open-source
Simulating user interactions to study behavior in recommendation systems.
Testing and refining recommendation algorithms with realistic user simulations.
Analyzing the impact of diverse user preferences on recommender performance.
Exploring phenomena such as the filter bubble effect in recommendation environments.
Conducting large-scale simulations without the need for real user studies.
Agent4Rec demonstrates high autonomy in simulating user behaviors through LLM-powered agents that independently interact with recommendation systems based on personalized profiles and memory modules. These agents autonomously perform actions (e.g., watching, rating) and conduct emotion-driven reflections without human intervention. However, their autonomy is constrained to predefined recommendation scenarios (e.g., movies) and relies on initial configurations from datasets like MovieLens-1M.
Open Source
Contact