增强记忆的LLM代理，让推荐更懂跨域兴趣与热门影响
AgentCF++: Memory-enhanced LLM-based Agents for Popularity-aware Cross-domain Recommendations
- 双层记忆+两步融合，减少跨域决策中的无关信息
- 引入兴趣组与共享记忆，捕捉用户群体流行趋势
- 适合研究跨域推荐与用户行为建模的开发者
基于大语言模型的用户代理通过模拟用户交互行为，正成为提升推荐系统性能的新兴方法。在真实场景中，用户行为常具跨域特性并受他人影响。现有方法因记忆设计缺陷，在跨域场景下会引入大量无关信息，且难以识别其他用户行为带来的影响（如流行度因素）。为此，我们提出双层记忆架构与两步融合机制，有效避免决策过程中的冗余信息，同时实现跨域偏好的高效整合。此外，引入兴趣组与组共享记忆，更好捕捉相似兴趣用户间流行度的影响。大量实验验证了AgentCF++的有效性。代码已开源：https://github.com/jhliu0807/AgentCF-plus。
原文摘要 · Abstract (English)
LLM-based user agents, which simulate user interaction behavior, are emerging as a promising approach to enhancing recommender systems. In real-world scenarios, users' interactions often exhibit cross-domain characteristics and are influenced by others. However, the memory design in current methods causes user agents to introduce significant irrelevant information during decision-making in cross-domain scenarios and makes them unable to recognize the influence of other users' interactions, such as popularity factors. To tackle this issue, we propose a dual-layer memory architecture combined with a two-step fusion mechanism. This design avoids irrelevant information during decision-making while ensuring effective integration of cross-domain preferences. We also introduce the concepts of interest groups and group-shared memory to better capture the influence of popularity factors on users with similar interests. Comprehensive experiments validate the effectiveness of AgentCF++. Our code is available at https://github.com/jhliu0807/AgentCF-plus.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。