While semantic ID-based generative retrieval enables efficient end-to-end modeling in industrial applications, these methods face a persistent trade-off: head items are susceptible to ID collisions that negatively impact downstream tasks, whereas data-sparse tail items, including cold-start items, exhibit limited generalization. To address this issue, we propose the Anchored Curriculum with Sequential Adaptive Quantization (SA^2CRQ) framework. The framework introduces Sequential Adaptive Residual Quantization (SARQ) to dynamically allocate code lengths based on item path entropy, assigning longer, discriminative IDs to head items and shorter, generalizable IDs to tail items. To mitigate data sparsity, the Anchored Curriculum Residual Quantization (ACRQ) component utilizes a frozen semantic manifold learned from head items to regularize and accelerate the representation learning of tail items. Experimental results from a large-scale industrial search system and multiple public datasets indicate that SA^2CRQ yields consistent improvements over existing baselines, particularly in cold-start retrieval scenarios.

翻译：尽管基于语义ID的生成式检索在工业应用中实现了高效的端到端建模，这些方法始终面临一个权衡问题：头部商品易受ID冲突影响，从而对下游任务产生负面影响；而数据稀疏的尾部商品（包括冷启动商品）则表现出有限的泛化能力。为解决这一问题，我们提出了锚定课程与序列自适应量化（SA^2CRQ）框架。该框架引入了序列自适应残差量化（SARQ），根据商品路径熵动态分配编码长度，为头部商品分配更长、更具区分性的ID，为尾部商品分配更短、更具泛化性的ID。为缓解数据稀疏问题，锚定课程残差量化（ACRQ）组件利用从头部商品学习到的冻结语义流形，来规范并加速尾部商品的表示学习。来自大规模工业搜索系统和多个公开数据集的实验结果表明，SA^2CRQ相较于现有基线方法取得了持续改进，尤其在冷启动检索场景中表现突出。