快手提出UAGR：让生成式推荐对齐用户效用的两个关键改进
Utility-Aware Generative Recommendation: Utility-Enriched Semantic Codes and Utility-Guided Decoding
快手把推荐系统的打分逻辑直接嵌进生成式解码里，线上看完播和长观看这类信号，观看时长涨了0.206%，做推荐的可以看看思路。
Kuaishou 团队提出 UAGR，针对生成式推荐中语义标识符（SID）只编码内容语义、忽略分享和完播等曝光后行为的问题。方法包含两部分：Utility-Enriched Semantic Codes 在不增加 SID 长度和词表大小的前提下注入条目级效用信号，并支持增量更新；Utility-Guided Decoding 将多个曝光后结果的预测融合进 beam search 打分，避免高效用路径被提前剪枝。离线实验和线上 A/B 测试显示，该方法已在 Kuaishou 全量部署，视频观看时长提升 0.206%。
Utility-Aware Generative Recommendation: Utility-Enriched Semantic Codes and Utility-Guided Decoding
Generative recommendation has been widely adopted in large-scale industrial recommendation systems, where multimodal item embeddings are quantized into offline semantic identifiers (SIDs) and items are retrieved by autoregressively generating their SIDs. However, conventional SID construction often underrepresents item utility reflected in post-exposure behaviors such as shares, long views, and video completion, making semantically similar items with different utility insufficiently distinguishable while struggling to accommodate rapidly changing utility signals. Moreover, generation likelihood may be misaligned with downstream utility, causing high-utility candidates to be prematurely pruned during beam search before post-generation reranking or training-time reward alignment can effectively compensate. To address these limitations, we propose UAGR, which aligns both SID construction and decoding with downstream multi-objective utility. Our Utility-Enriched Semantic Codes preserve the original semantic information while incorporating item-level utility without increasing SID length or vocabulary size, supporting incremental utility updates with no additional tokenization or sequence-decoding cost. Meanwhile, our Utility-Guided Decoding estimates candidate utility by combining predictions of multiple post-exposure outcomes and incorporates these estimates into beam scoring, reducing the risk of prematurely pruning high-utility paths while enabling flexible utility control without interfering with generative backbone training. Extensive offline experiments and online A/B tests under real-world traffic demonstrate the effectiveness and deployability of UAGR, which has been fully deployed on Kuaishou and increases video watch time by 0.206\% online.
