Harnessing the reasoning power of Large Language Models (LLMs) for recommender systems is hindered by two fundamental challenges. First, current approaches lack a mechanism for automated, data-driven discovery of effective reasoning patterns, relying instead on brittle manual templates or unstable zero-shot prompting. Second, they employ structure-collapsing integration: direct prompting incurs prohibitive online inference costs, while feature extraction collapses reasoning chains into single vectors, discarding stepwise logic. To address these challenges, we propose SCoTER (Structured Chain-of-Thought Transfer for Enhanced Recommendation), a unified framework that treats pattern discovery and structure-aware transfer as a jointly optimized problem. Specifically, SCoTER operationalizes this through two synergistic components: a GVM pipeline for automated pattern discovery and a structure-preserving integration architecture that transfers stepwise logic to efficient models. Formally, we provide information-theoretic justification proving that structure-preserving transfer achieves tighter performance bounds than structure-agnostic alternatives. Empirically, experiments on four benchmarks demonstrate improvements of 3.75\%-11.59\% over a strong TIGER backbone. Moreover, in production deployment on the Tencent Advertising Platform, SCoTER achieved a 2.14\% lift in Gross Merchandise Value (GMV) while eliminating online LLM inference costs. Overall, SCoTER establishes a principled and production-validated blueprint for transferring structured LLM reasoning to large-scale recommender systems.

翻译：利用大型语言模型（LLM）的推理能力构建推荐系统面临两个根本性挑战。首先，现有方法缺乏自动化、数据驱动的有效推理模式发现机制，主要依赖脆弱的手动模板或不稳定的零样本提示。其次，它们采用结构坍塌的集成方式：直接提示法导致在线推理成本过高，而特征提取法将推理链压缩为单一向量，丢弃了逐步逻辑。为应对这些挑战，我们提出了SCoTER（用于增强推荐的结构化思维链迁移），这是一个将模式发现与结构感知迁移作为联合优化问题的统一框架。具体而言，SCoTER通过两个协同组件实现这一目标：用于自动化模式发现的GVM流水线，以及将逐步逻辑迁移到高效模型的结构保持集成架构。在形式上，我们提供了信息论证明，表明结构保持迁移比无视结构的替代方案具有更严格的性能上界。实证方面，在四个基准测试上的实验显示，相比强大的TIGER骨干模型，性能提升了3.75%至11.59%。此外，在腾讯广告平台的生产部署中，SCoTER实现了2.14%的商品交易总额（GMV）提升，同时完全消除了在线LLM推理成本。总体而言，SCoTER为将结构化LLM推理迁移至大规模推荐系统提供了一个原则性且经过生产验证的蓝图。