The sequential recommendation (SR) task aims to predict the next item based on users' historical interaction sequences. Typically trained on historical data, SR models often struggle to adapt to real-time preference shifts during inference due to challenges posed by distributional divergence and parameterized constraints. Existing approaches to address this issue include test-time training, test-time augmentation, and retrieval-augmented fine-tuning. However, these methods either introduce significant computational overhead, rely on random augmentation strategies, or require a carefully designed two-stage training paradigm. In this paper, we argue that the key to effective test-time adaptation lies in achieving both effective augmentation and efficient adaptation. To this end, we propose Retrieve-then-Adapt (ReAd), a novel framework that dynamically adapts a deployed SR model to the test distribution through retrieved user preference signals. Specifically, given a trained SR model, ReAd first retrieves collaboratively similar items for a test user from a constructed collaborative memory database. A lightweight retrieval learning module then integrates these items into an informative augmentation embedding that captures both collaborative signals and prediction-refinement cues. Finally, the initial SR prediction is refined via a fusion mechanism that incorporates this embedding. Extensive experiments across five benchmark datasets demonstrate that ReAd consistently outperforms existing SR methods.

翻译：序列推荐（SR）任务旨在基于用户历史交互序列预测下一物品。通常基于历史数据训练的SR模型，因分布偏移和参数化约束，难以在推理阶段适应实时的偏好变化。现有解决方法包括测试时训练、测试时增强及检索增强微调，但这些方法或引入显著计算开销，或依赖随机增强策略，或需精心设计的两阶段训练范式。本文认为，有效实现测试时自适应的关键在于同时达成增强效果与适应效率。为此，我们提出Retrieve-then-Adapt（ReAd）——一种通过检索用户偏好信号动态调整已部署SR模型以适配测试分布的新框架。具体而言，给定训练好的SR模型，ReAd首先从构建的协同记忆数据库中为目标用户检索协同性相似物品；随后，轻量级检索学习模块将这些物品整合为信息增强嵌入，同时捕捉协同信号与预测优化线索；最终，通过融合该嵌入的机制优化初始SR预测结果。在五个基准数据集上的广泛实验表明，ReAd始终优于现有SR方法。