Large Language Models (LLMs) empower recommendation systems through their advanced reasoning and planning capabilities. However, the dynamic nature of user interests and content poses a significant challenge: While initial fine-tuning aligns LLMs with domain knowledge and user preferences, it fails to capture such real-time changes, necessitating robust update mechanisms. This paper investigates strategies for updating LLM-powered recommenders, focusing on the trade-offs between ongoing fine-tuning and Retrieval-Augmented Generation (RAG). Using an LLM-powered user interest exploration system as a case study, we perform a comparative analysis of these methods across dimensions like cost, agility, and knowledge incorporation. We propose a hybrid update strategy that leverages the long-term knowledge adaptation of periodic fine-tuning with the agility of low-cost RAG. We demonstrate through live A/B experiments on a billion-user platform that this hybrid approach yields statistically significant improvements in user satisfaction, offering a practical and cost-effective framework for maintaining high-quality LLM-powered recommender systems.

翻译：大型语言模型（LLM）凭借其先进的推理与规划能力，为推荐系统提供了强大支持。然而，用户兴趣与内容的动态性构成了重大挑战：尽管初始微调能使LLM与领域知识及用户偏好对齐，却无法捕捉此类实时变化，因此需要稳健的更新机制。本文研究了LLM驱动推荐系统的更新策略，重点关注持续微调与检索增强生成（RAG）之间的权衡。以LLM驱动的用户兴趣探索系统为案例，我们从成本、敏捷性、知识融合等维度对这些方法进行了比较分析。我们提出一种混合更新策略，该策略结合了周期性微调的长期知识适应能力与低成本RAG的敏捷性。通过在亿级用户平台上进行的线上A/B实验，我们证明该混合方法在用户满意度方面取得了统计显著的提升，为维持高质量LLM驱动推荐系统提供了一个实用且经济高效的框架。