Reasoning in Large Language Models (LLMs) has recently shown strong potential in enhancing generative recommendation through deep understanding of complex user preference. Existing approaches follow a {reason-then-recommend} paradigm, where LLMs perform step-by-step reasoning before item generation. However, this paradigm inevitably suffers from reasoning degradation (i.e., homogeneous or error-accumulated reasoning) due to the lack of intermediate verification, thus undermining the recommendation. To bridge this gap, we propose a novel \textbf{\textit{reason-verify-recommend}} paradigm, which interleaves reasoning with verification to provide reliable feedback, guiding the reasoning process toward more faithful user preference understanding. To enable effective verification, we establish two key principles for verifier design: 1) reliability ensures accurate evaluation of reasoning correctness and informative guidance generation; and 2) multi-dimensionality emphasizes comprehensive verification across multi-dimensional user preferences. Accordingly, we propose an effective implementation called VRec. It employs a mixture of verifiers to ensure multi-dimensionality, while leveraging a proxy prediction objective to pursue reliability. Experiments on four real-world datasets demonstrate that VRec substantially enhances recommendation effectiveness and scalability without compromising efficiency. The codes can be found at https://github.com/Linxyhaha/Verifiable-Rec.

翻译：大语言模型（LLM）中的推理近期展现出通过深度理解复杂用户偏好来增强生成推荐的强大潜力。现有方法遵循一种“先推理后推荐”的范式，即LLM在生成推荐项之前执行逐步推理。然而，由于缺乏中间验证，该范式不可避免地遭受推理退化（即同质化或误差累积的推理）问题，从而损害推荐效果。为弥补这一差距，我们提出了一种新颖的**“推理-验证-推荐”**范式，该范式将推理与验证交织进行，以提供可靠的反馈，引导推理过程走向更忠实于用户偏好的理解。为实现有效验证，我们为验证器设计确立了两个关键原则：1）可靠性确保对推理正确性的准确评估和信息丰富的指导生成；2）多维度强调跨多维度用户偏好的全面验证。据此，我们提出了一种名为VRec的有效实现。它采用混合验证器来确保多维度性，同时利用代理预测目标来追求可靠性。在四个真实世界数据集上的实验表明，VRec在不牺牲效率的前提下，显著提升了推荐效果和可扩展性。代码可在 https://github.com/Linxyhaha/Verifiable-Rec 找到。