Large Language Models (LLMs) demonstrate significant advantages in leveraging structured world knowledge and multi-step reasoning capabilities. However, fundamental challenges arise when transforming LLMs into real-world recommender systems due to semantic and behavioral misalignment. To bridge this gap, we propose Align$^3$GR, a novel framework that unifies token-level, behavior modeling-level, and preference-level alignment. Our approach introduces: Dual tokenization fusing user-item semantic and collaborative signals. Enhanced behavior modeling with bidirectional semantic alignment. Progressive DPO strategy combining self-play (SP-DPO) and real-world feedback (RF-DPO) for dynamic preference adaptation. Experiments show Align$^3$GR outperforms the SOTA baseline by +17.8% in Recall@10 and +20.2% in NDCG@10 on the public dataset, with significant gains in online A/B tests and full-scale deployment on an industrial large-scale recommendation platform.

翻译：大语言模型（LLMs）在利用结构化世界知识与多步推理能力方面展现出显著优势。然而，将LLMs转化为实际推荐系统时，语义与行为层面的错位带来了根本性挑战。为弥合此鸿沟，我们提出Align$^3$GR——一种统一令牌级、行为建模级与偏好级对齐的新型框架。该方法包含：融合用户-物品语义与协同信号的双重令牌化机制；通过双向语义对齐增强的行为建模；结合自博弈（SP-DPO）与真实世界反馈（RF-DPO）的动态偏好适应渐进式DPO策略。实验表明，在公开数据集上，Align$^3$GR在Recall@10与NDCG@10指标上分别超越当前最佳基线+17.8%与+20.2%，并在工业级大规模推荐平台的在线A/B测试与全量部署中取得显著效果提升。