Generative recommendation has emerged as a transformative paradigm for capturing the dynamic evolution of user intents in sequential recommendation. While flow-based methods improve the efficiency of diffusion models, they remain hindered by the ``Noise-to-Data'' paradigm, which introduces two critical inefficiencies: prior mismatch, where generation starts from uninformative noise, forcing a lengthy recovery trajectory; and linear redundancy, where iterative solvers waste computation on modeling deterministic preference transitions. To address these limitations, we propose a Flow-based Average Velocity Establishment (Fave) framework for one-step generation recommendation that learns a direct trajectory from an informative prior to the target distribution. Fave is structured via a progressive two-stage training strategy. In Stage 1, we establish a stable preference space through dual-end semantic alignment, applying constraints at both the source (user history) and target (next item) to prevent representation collapse. In Stage 2, we directly resolve the efficiency bottlenecks by introducing a semantic anchor prior, which initializes the flow with a masked embedding from the user's interaction history, providing an informative starting point. Then we learn a global average velocity, consolidating the multi-step trajectory into a single displacement vector, and enforce trajectory straightness via a JVP-based consistency constraint to ensure one-step generation. Extensive experiments on three benchmarks demonstrate that Fave not only achieves state-of-the-art recommendation performance but also delivers an order-of-magnitude improvement in inference efficiency, making it practical for latency-sensitive scenarios.

翻译：生成式推荐已成为捕捉序列推荐中用户意图动态演变的变革性范式。基于流的方法虽提升了扩散模型的效率，但仍受限于"噪声到数据"范式，这引入了两个关键的低效问题：先验不匹配（从无信息噪声开始生成，迫使恢复轨迹冗长）和线性冗余（迭代求解器在建模确定性偏好转换时浪费计算）。为解决这些局限，我们提出了基于流的平均速度建立（Fave）框架，用于一步生成式推荐，该框架学习从信息丰富的先验到目标分布的直接轨迹。Fave通过渐进式两阶段训练策略构建。在第一阶段，我们通过双端语义对齐建立稳定的偏好空间，在源端（用户历史）和目标端（下一项）同时施加约束以防止表示坍塌。第二阶段，我们直接解决效率瓶颈：引入语义锚点先验（使用用户交互历史的掩码嵌入初始化流，提供信息丰富的起点），学习全局平均速度（将多步轨迹整合为单一位移向量），并通过基于JVP的一致性约束强制轨迹直线性以确保一步生成。在三个基准上的大量实验表明，Fave不仅实现了最先进的推荐性能，还将推理效率提升了一个数量级，使其适用于延迟敏感场景。