Generative Recommendation (GenRec) models reformulate recommendation as a sequence generation task, representing items as discrete Semantic IDs used symmetrically as both inputs and prediction targets. We identify a critical dual-stage information bottleneck in this design: (1) the Input Bottleneck, where lossy quantization degrades fine-grained semantics, while popularity bias skews the learned representations toward frequent items, and (2) the Output Bottleneck, where imprecise discrete targets limit supervision quality. To address these issues, we propose AsymRec, an asymmetric continuous-discrete framework that decouples input and output representations. Specifically, Multi-expert Semantic Projection (MSP) maps continuous embeddings into the Transformer's hidden space via expert-specialized projections, preserving semantic richness and improving generalization to infrequent items. Multi-faceted Hierarchical Quantization (MHQ) constructs high-capacity, structured discrete targets through multi-view and multi-level quantization with semantic regularization, preventing dimensional collapse while retaining fine-grained distinctions. Extensive experiments demonstrate that AsymRec consistently outperforms state-of-the-art generative recommenders by an average of 15.8 %. The code will be released.

翻译：生成式推荐（GenRec）模型将推荐任务重构为序列生成任务，将物品表示为离散语义ID，对称地用作输入和预测目标。我们发现该设计存在双重信息瓶颈：(1) 输入瓶颈——有损量化会削弱细粒度语义，同时流行度偏差使学习到的表征偏向高频物品；(2) 输出瓶颈——不精确的离散目标限制了监督质量。为解决这些问题，我们提出AsymRec——一种非对称连续-离散框架，将输入和输出表征解耦。具体而言，多专家语义投影（MSP）通过专家特化投影将连续嵌入映射至Transformer隐空间，在保留语义丰富性的同时提升对低频物品的泛化能力。多面分层量化（MHQ）通过多视角、多层次量化结合语义正则化构建高容量、结构化的离散目标，在保持细粒度区分的同时防止维度坍缩。大量实验表明，AsymRec相较于最先进的生成式推荐器平均提升15.8%。相关代码将予以开源。