Recommender systems serve as foundational infrastructure in modern information ecosystems, helping users navigate digital content and discover items aligned with their preferences. At their core, recommender systems address a fundamental problem: matching users with items. Over the past decades, the field has experienced successive paradigm shifts, from collaborative filtering and matrix factorization in the machine learning era to neural architectures in the deep learning era. Recently, the emergence of generative models, especially large language models (LLMs) and diffusion models, have sparked a new paradigm: generative recommendation, which reconceptualizes recommendation as a generation task rather than discriminative scoring. This survey provides a comprehensive examination through a unified tripartite framework spanning data, model, and task dimensions. Rather than simply categorizing works, we systematically decompose approaches into operational stages-data augmentation and unification, model alignment and training, task formulation and execution. At the data level, generative models enable knowledge-infused augmentation and agent-based simulation while unifying heterogeneous signals. At the model level, we taxonomize LLM-based methods, large recommendation models, and diffusion approaches, analyzing their alignment mechanisms and innovations. At the task level, we illuminate new capabilities including conversational interaction, explainable reasoning, and personalized content generation. We identify five key advantages: world knowledge integration, natural language understanding, reasoning capabilities, scaling laws, and creative generation. We critically examine challenges in benchmark design, model robustness, and deployment efficiency, while charting a roadmap toward intelligent recommendation assistants that fundamentally reshape human-information interaction.

翻译：推荐系统作为现代信息生态中的基础架构，帮助用户浏览数字内容并发现符合其偏好的项目。其核心在于解决一个基本问题：将用户与项目进行匹配。过去几十年间，该领域经历了连续的范式转变，从机器学习时代的协同过滤与矩阵分解，到深度学习时代的神经架构。近年来，生成模型（尤其是大语言模型与扩散模型）的出现催生了新范式：生成式推荐，其将推荐重新定义为生成任务而非判别性评分。本综述通过涵盖数据、模型与任务维度的统一三元框架进行全面审视。我们不仅对现有工作进行分类，更系统性地将方法分解为操作阶段：数据增强与统一、模型对齐与训练、任务构建与执行。在数据层面，生成模型实现了知识增强的数据扩充与基于智能体的模拟，同时统一了异构信号。在模型层面，我们系统归类基于大语言模型的方法、大型推荐模型及扩散方法，分析其对齐机制与创新点。在任务层面，我们阐明了包括对话式交互、可解释推理与个性化内容生成在内的新能力。我们总结了五大关键优势：世界知识整合、自然语言理解、推理能力、缩放定律与创造性生成。我们批判性审视了基准设计、模型鲁棒性与部署效率等方面的挑战，并绘制了通往智能推荐助手的路线图，该助手将从根本上重塑人机信息交互模式。