Large Language Model (LLM)-based user agents have emerged as a powerful tool for improving recommender systems by simulating user interactions. However, existing methods struggle with cross-domain scenarios due to inefficient memory structures, leading to irrelevant information retention and failure to account for social influence factors such as popularity. To address these limitations, we introduce AgentCF++, a novel framework featuring a dual-layer memory architecture and a two-step fusion mechanism to filter domain-specific preferences effectively. Additionally, we propose interest groups with shared memory, allowing the model to capture the impact of popularity trends on users with similar interests. Through extensive experiments on multiple cross-domain datasets, AgentCF++ demonstrates superior performance over baseline models, highlighting its effectiveness in refining user behavior simulation for recommender systems. Our code is available at https://anonymous.4open.science/r/AgentCF-plus.

本研究解决了现有基于大型语言模型的用户代理在跨域推荐中因内存结构低效而导致的信息相关性不足及忽视社会影响因素的问题。提出的AgentCF++框架通过双层内存架构和两步融合机制，有效过滤域特定偏好，并通过共享内存的兴趣小组捕捉流行趋势的影响，实验结果表明其在多个跨域数据集上的表现优于基线模型，突显了其改进用户行为模拟的有效性。

基于内存优化的LLM用户代理提升跨域推荐系统