Generative recommendation is emerging as a transformative paradigm by directly generating recommended items, rather than relying on matching. Building such a system typically involves two key components: (1) optimizing the tokenizer to derive suitable item identifiers, and (2) training the recommender based on those identifiers. Existing approaches often treat these components separately--either sequentially or in alternation--overlooking their interdependence. This separation can lead to misalignment: the tokenizer is trained without direct guidance from the recommendation objective, potentially yielding suboptimal identifiers that degrade recommendation performance. To address this, we propose BLOGER, a Bi-Level Optimization for GEnerative Recommendation framework, which explicitly models the interdependence between the tokenizer and the recommender in a unified optimization process. The lower level trains the recommender using tokenized sequences, while the upper level optimizes the tokenizer based on both the tokenization loss and recommendation loss. We adopt a meta-learning approach to solve this bi-level optimization efficiently, and introduce gradient surgery to mitigate gradient conflicts in the upper-level updates, thereby ensuring that item identifiers are both informative and recommendation-aligned. Extensive experiments on multiple real-world datasets demonstrate that BLOGER consistently outperforms state-of-the-art generative recommendation methods while maintaining practical efficiency with no significant additional computational overhead, effectively bridging the gap between item tokenization and autoregressive generation. We release our code at https://github.com/Ten-Mao/BLOGER.

翻译：生成式推荐作为一种变革性范式正在兴起，它直接生成推荐项而非依赖匹配。构建此类系统通常涉及两个关键组件：（1）优化分词器以导出合适的物品标识符；（2）基于这些标识符训练推荐模型。现有方法常将这些组件独立处理——无论是顺序执行还是交替进行——忽视了它们之间的相互依赖性。这种分离可能导致不对齐：分词器在没有推荐目标直接指导的情况下训练，可能产生次优标识符，从而降低推荐性能。为解决此问题，我们提出BLOGER——一个面向生成式推荐的双层优化框架，该框架在统一的优化过程中显式建模分词器与推荐器之间的相互依赖关系。下层利用分词序列训练推荐器，而上层则基于分词损失和推荐损失联合优化分词器。我们采用元学习方法高效求解该双层优化问题，并引入梯度剪裁以缓解上层更新中的梯度冲突，从而确保物品标识符既信息丰富又与推荐目标对齐。在多个真实数据集上的广泛实验表明，BLOGER在保持实际效率且无显著额外计算开销的同时，始终优于最先进的生成式推荐方法，有效弥合了物品分词与自回归生成之间的鸿沟。我们已在https://github.com/Ten-Mao/BLOGER 公开代码。