Industrial recommender systems critically depend on high-quality ranking models. However, traditional pipelines still rely on manual feature engineering and scenario-specific architectures, which hinder cross-scenario transfer and large-scale deployment. To address these challenges, we propose \textbf{MTmixAtt}, a unified Mixture-of-Experts (MoE) architecture with Multi-Mix Attention, designed for large-scale recommendation tasks. MTmixAtt integrates two key components. The \textbf{AutoToken} module automatically clusters heterogeneous features into semantically coherent tokens, removing the need for human-defined feature groups. The \textbf{MTmixAttBlock} module enables efficient token interaction via a learnable mixing matrix, shared dense experts, and scenario-aware sparse experts, capturing both global patterns and scenario-specific behaviors within a single framework. Extensive experiments on the industrial TRec dataset from Meituan demonstrate that MTmixAtt consistently outperforms state-of-the-art baselines including Transformer-based models, WuKong, HiFormer, MLP-Mixer, and RankMixer. At comparable parameter scales, MTmixAtt achieves superior CTR and CTCVR metrics; scaling to MTmixAtt-1B yields further monotonic gains. Large-scale online A/B tests validate the real-world impact: in the \textit{Homepage} scenario, MTmixAtt increases Payment PV by \textbf{+3.62\%} and Actual Payment GTV by \textbf{+2.54\%}. Overall, MTmixAtt provides a unified and scalable solution for modeling arbitrary heterogeneous features across scenarios, significantly improving both user experience and commercial outcomes.

翻译：工业推荐系统高度依赖于高质量的排序模型。然而，传统流程仍依赖于人工特征工程和特定场景架构，这阻碍了跨场景迁移和大规模部署。为应对这些挑战，我们提出了 **MTmixAtt**，一种集成多混合注意力的统一混合专家（MoE）架构，专为大规模推荐任务设计。MTmixAtt 包含两个核心组件。**AutoToken** 模块自动将异构特征聚类成语义连贯的令牌，无需人工定义特征分组。**MTmixAttBlock** 模块通过可学习的混合矩阵、共享的稠密专家和场景感知的稀疏专家，实现高效的令牌交互，在单一框架内同时捕获全局模式和场景特定行为。在美团工业级 TRec 数据集上的大量实验表明，MTmixAtt 持续优于包括基于 Transformer 的模型、WuKong、HiFormer、MLP-Mixer 和 RankMixer 在内的最先进基线模型。在参数量相当的情况下，MTmixAtt 实现了更优的 CTR 和 CTCVR 指标；扩展至 MTmixAtt-1B 模型可带来进一步的单调性能提升。大规模在线 A/B 测试验证了其实践影响：在 **首页** 场景中，MTmixAtt 使支付 PV 提升 **+3.62%**，实际支付 GTV 提升 **+2.54%**。总体而言，MTmixAtt 为跨场景任意异构特征建模提供了一个统一且可扩展的解决方案，显著改善了用户体验和商业效果。