用智能体重构推荐系统，实现自动进化与多目标优化。
Rethinking Recommendation Paradigms: From Pipelines to Agentic Recommender Systems
- 将推荐模块升级为可独立评估的智能体，形成闭环决策单元。
- 提出强化学习与大模型生成两种自进化机制，支持架构与训练方案动态优化。
- 支持单智能体演化与多智能体协同演化，适合复杂业务场景的推荐系统
大规模工业推荐系统通常采用固定的多阶段流水线（召回、排序、重排），并从协同过滤发展到深度和大规模预训练模型。然而，无论是多阶段设计还是所谓的“一体模型”架构，本质上仍为静态结构：模型是黑箱，系统优化依赖人工假设与工程迭代，在异构数据与多目标业务约束下难以扩展。本文提出一种智能体推荐系统（AgenticRS），将关键模块重组为智能体。只有当模块具备功能闭环、可独立评估且拥有可演化的决策空间时，才被提升为智能体。对于模型智能体，我们提出两种自进化机制：在明确动作空间中使用类强化学习优化，以及在开放设计空间中利用大语言模型生成并筛选新架构与训练方案。进一步区分单个智能体的个体演化与多个智能体间的选择与连接方式的组合演化，并采用分层内外奖励机制，将局部优化与全局目标耦合。这为将静态流水线转化为自演化智能体推荐系统提供了清晰蓝图。
原文摘要 · Abstract (English)
Large-scale industrial recommenders typically use a fixed multi-stage pipeline (recall, ranking, re-ranking) and have progressed from collaborative filtering to deep and large pre-trained models. However, both multi-stage and so-called One Model designs remain essentially static: models are black boxes, and system improvement relies on manual hypotheses and engineering, which is hard to scale under heterogeneous data and multi-objective business constraints. We propose an Agentic Recommender System (AgenticRS) that reorganizes key modules as agents. Modules are promoted to agents only when they form a functionally closed loop, can be independently evaluated, and possess an evolvable decision space. For model agents, we outline two self-evolution mechanisms: reinforcement learning style optimization in well-defined action spaces, and large language model based generation and selection of new architectures and training schemes in open-ended design spaces. We further distinguish individual evolution of single agents from compositional evolution over how multiple agents are selected and connected, and use a layered inner and outer reward design to couple local optimization with global objectives. This provides a concise blueprint for turning static pipelines into self-evolving agentic recommender systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。