发表机构
Tencent’s PCG (Platform and Content Group)（腾讯平台与内容事业群）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出TGR工业级推荐框架，通过CCFormer、BARGE、HiGR、TGR-Reason四个模块，解决传统推荐系统的缺陷，在多个场景取得显著指标提升，已部署服务数亿用户。
AI 中文摘要
工业级推荐系统通常依赖级联的召回、预排序、排序和重排序阶段，这些分别优化的模型限制了系统扩展性，导致决策碎片化，且缺乏语义知识与推理能力。我们提出TGR（腾讯生成式推荐，Tencent Generative Recommendation），这是一个沿三个耦合方向将推荐推向生成式范式的工业级框架。TGR-GenRank通过CCFormer升级排序模块，该模型结合了统一特征标记、可扩展Transformer主干、特征-场分离交叉注意力、子空间标记混合以及分层序列压缩，同时保留了每个物品的多任务输出。TGR-GenRec在两种范式下探索端到端生成：BARGE通过物品上下文感知注意力、分层路径重排序和正交双路径解码，解决分层语义-ID生成中的物品边界损失和语义漂移问题；HiGR则采用前缀结构语义-ID、粗到细解码和列表级多目标对齐执行整个推荐列表的生成。TGR-Reason将离线生成的语义-ID推理标记注入在线解码过程，无需在请求时展开即可提供推理能力。TGR已部署在腾讯多个生产场景中，服务数亿用户。CCFormer在五个A/B测试场景中取得显著提升，其中两个场景已全面上线，包括点击率（CTR）提升3.57%，广告收入提升1.71%；BARGE全面上线后，命中率（Hit@5）提升10.2-16.9%，点击率提升0.60%，阅读时间提升1.70%；HiGR将离线推荐列表质量提升15.9-21.3%，推理速度提升5倍，且实现观看时长最高提升1.22%，视频播放量提升1.73%；TGR-Reason使冷启动新用户的命中率（Hit@1）提升477.8%，有效消费提升1.75%，新用户曝光转化率提升13.09%。
英文摘要
Industrial recommender systems typically rely on cascaded retrieval, pre-ranking, ranking, and reranking stages, whose separately optimized models limit scaling, fragment decision making, and lack semantic knowledge and reasoning. We present TGR (Tencent Generative Recommendation), an industrial framework that advances recommendation toward the generative paradigm along three coupled directions. TGR-GenRank upgrades ranking through CCFormer, which combines unified feature tokenization, a scalable Transformer backbone, feature-field separated cross attention, subspace token mixing, and hierarchical sequence compression while retaining per-item multi-task outputs. TGR-GenRec explores end-to-end generation under two paradigms: BARGE bridges item-boundary loss and semantic drift in hierarchical semantic-ID generation through item context-aware attention, hierarchical path reranking, and orthogonal dual-path decoding; HiGR performs whole-slate generation with prefix-structured semantic IDs, coarse-to-fine decoding, and listwise multi-objective alignment. TGR-Reason injects offline-generated semantic-ID reason tokens into online decoding, providing reasoning without request-time rollout. TGR is deployed across Tencent production surfaces serving hundreds of millions of users. CCFormer delivers significant gains in five A/B-tested scenarios and is fully launched in two, including +3.57% CTR and +1.71% advertising revenue. BARGE improves Hit@5 by 10.2-16.9% and yields +0.60% CTR and +1.70% reading time after full rollout. HiGR improves offline slate quality by 15.9-21.3% with a 5x inference speedup and achieves up to +1.22% watch time and +1.73% video views. TGR-Reason raises cold-start new-user Hit@1 by 477.8% and delivers +1.75% effective consumption and +13.09% new-user exposure-to-conversion online.
