发表机构
Meta Platforms（元平台公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出基于LLM的智能体推荐框架SYF，采用三层架构实现实时多模态内容协同策划，经离线评估与在线A/B实验验证，可提升信息流相关性与用户情感，为工业场景提供交互式推荐方案。
AI 中文摘要
工业推荐系统大多采用被动排序范式，该范式从点击、停留时长等隐式行为信号中推断用户偏好，而非从明确的自然语言输入中获取。这导致用户的明确兴趣与被动行为算法推送内容之间持续存在差距，限制了用户表达细致偏好或实时调整信息流的能力。为解决推荐优化方式与用户表达兴趣方式之间日益扩大的差距，本文提出Shape Your Feed（SYF），这是一种基于大语言模型（LLM）的智能体推荐框架，支持内容的实时多模态协同策划。SYF采用三层架构：（i）感知流（Perception Flow），从文本提示、语音命令和UI交互中捕捉细粒度用户意图；（ii）服务流（Serving Flow），基于编码用户不断变化偏好的持久语义画像（Semantic Profile），对候选项目进行实时智能体重排序与剪枝；（iii）自进化流（Self-Evolution Flow），通过直接偏好优化（Direct Preference Optimization, DPO）和大语言模型作为评判者的集成，使系统行为与人类判断对齐。离线评估显示，SYF的对齐评分模块准确率达98.85%，大幅优于强少样本基线。针对生产流量的大规模在线A/B实验进一步表明，SYF提升了信息流相关性与用户情感，为工业场景中交互式、用户可操控的推荐系统提供了实用且可扩展的路径。
英文摘要
Industrial recommendation systems predominantly adopt a passive ranking paradigm that infers user preferences from implicit behavioral signals (e.g., clicks, dwell time) rather than explicit, natural language inputs. As a result, users experience a persistent discrepancy between their explicit interests and what passive behavioral algorithms deliver, limiting their ability to express nuanced preferences or steer their feed in real time. To address this growing gap between how recommendations are optimized and how users wish to articulate their interests, we present Shape Your Feed (SYF), an LLM-based agentic recommendation framework that enables real-time, multimodal co-curation of content. SYF employs a three-tier architecture: (i) a Perception Flow that captures fine-grained user intent from text prompts, voice commands, and UI interactions; (ii) a Serving Flow that performs real-time agentic re-ranking and pruning of candidate items, grounded in a persistent Semantic Profile encoding evolving user preferences; and (iii) a Self-Evolution Flow that aligns system behavior with human judgments via Direct Preference Optimization (DPO) and an LLM-as-a-Judge ensemble. Offline evaluations show that SYF's alignment scoring module achieves 98.85% accuracy, substantially improving over strong few-shot baselines. Large-scale online A/B experiments on production traffic further demonstrate that SYF improves feed relevance and user sentiment, indicating a practical and scalable path toward interactive, user-steerable recommendation in industrial settings.
CommentsAccepted in RecSys 2026 Industrial Track
