Recommender system has deeply revolutionized people's daily life and production, bringing a large amount of business value. In the recommendation domain, simulation and real data-based studies are two typical research paradigms, with each having different advantages. Previously, real data-based studies occupy more important positions, since accurately simulating the user preference is quite difficult. Recently, large language models (LLM) have shown great potential to achieve human-like intelligence, which provides new opportunities to overcome the shortcomings of simulation-based studies and thus highlight their advantages, such as much more application scenarios and cheaper data acquisition strategies. To shed lights on this direction, in this paper, we introduce an LLM-based recommender simulator called RecAgent. Our simulator is composed of two modules: (1) the user module and (2) the recommender module. The user module can browse the recommendation website, communicate with other users and broadcast messages on the social media. The recommender module is designed to provide search or recommendation lists to the users, and one can design different models to implement the recommender. All the users take actions based on LLMs, and can freely evolve like in the real world. We present several case studies to demonstrate that the users in our simulator can indeed behave in a reasonable manner as expected. Our project has been released at https://github.com/RUC-GSAI/YuLan-Rec.

翻译：推荐系统已深刻改变了人们的日常生活与生产活动，带来了巨大的商业价值。在推荐领域，基于模拟和基于真实数据的研究是两种典型的研究范式，各有其优势。以往，基于真实数据的研究占据更重要的地位，因为精准模拟用户偏好极其困难。近期，大语言模型（LLM）展现出实现类人智能的巨大潜力，这为克服基于模拟研究的固有缺陷、凸显其优势（例如更广泛的应用场景和更低的数据获取成本）提供了新机遇。为阐明这一方向，本文介绍了一种基于LLM的推荐模拟器——RecAgent。该模拟器由两大模块构成：（1）用户模块；（2）推荐模块。用户模块可浏览推荐网站、与其他用户交互以及在社交媒体发布消息；推荐模块则负责向用户提供搜索或推荐列表，且可设计不同模型实现推荐功能。所有用户基于LLM驱动行为，并像现实世界一样自由演化。我们通过多项案例研究表明，模拟器中的用户确实能以符合预期的合理方式行动。相关项目已发布在https://github.com/RUC-GSAI/YuLan-Rec。