In the wave of generative recommendation, we present OneMall, an end-to-end generative recommendation framework tailored for e-commerce services at Kuaishou. Our OneMall systematically unifies the e-commerce's multiple item distribution scenarios, such as Product-card, short-video and live-streaming. Specifically, it comprises three key components, aligning the entire model training pipeline to the LLM's pre-training/post-training: (1) E-commerce Semantic Tokenizer: we provide a tokenizer solution that captures both real-world semantics and business-specific item relations across different scenarios; (2) Transformer-based Architecture: we largely utilize Transformer as our model backbone, e.g., employing Query-Former for long sequence compression, Cross-Attention for multi-behavior sequence fusion, and Sparse MoE for scalable auto-regressive generation; (3) Reinforcement Learning Pipeline: we further connect retrieval and ranking models via RL, enabling the ranking model to serve as a reward signal for end-to-end policy retrieval model optimization. Extensive experiments demonstrate that OneMall achieves consistent improvements across all e-commerce scenarios: +13.01\% GMV in product-card, +15.32\% Orders in Short-Video, and +2.78\% Orders in Live-Streaming. OneMall has been deployed, serving over 400 million daily active users at Kuaishou.

翻译：在生成式推荐的浪潮中，我们提出了OneMall，一个为快手电商服务量身定制的端到端生成式推荐框架。我们的OneMall系统性地统一了电商的多种商品分发场景，例如商品卡片、短视频和直播。具体而言，它包含三个关键组件，将整个模型训练流程与LLM的预训练/后训练阶段对齐：(1) 电商语义分词器：我们提供了一种分词器解决方案，能够捕获跨不同场景的真实世界语义和业务特定的商品关系；(2) 基于Transformer的架构：我们广泛采用Transformer作为模型主干，例如，使用Query-Former进行长序列压缩，使用Cross-Attention进行多行为序列融合，以及使用稀疏MoE进行可扩展的自回归生成；(3) 强化学习流程：我们进一步通过RL连接检索和排序模型，使得排序模型能够作为端到端策略检索模型优化的奖励信号。大量实验表明，OneMall在所有电商场景中均取得了一致的性能提升：商品卡片场景GMV提升+13.01%，短视频场景订单量提升+15.32%，直播场景订单量提升+2.78%。OneMall已部署上线，服务于快手超过4亿的日活跃用户。