个性化很重要：在线购物中基于用户中心信息的长程对话智能体
原标题：Personalization Matters: Long-Horizon Conversation Agent with User-Centric Information in Online Shopping Interactions
AI 摘要
该论文提出一个多智能体、多模态RAG框架，用于在线购物中的长程对话个性化，将对话状态跟踪、推荐检索、偏好推理和回复生成解耦，并融合商品元数据、评论、图像描述和用户历史评论。在Amazon Reviews 2023基准上，启用检索的变体在轨迹级自动指标上平均得分4.82，高于无RAG基线的3.74；小规模真实用户研究中完整变体平均总体评分4.60，基线为2.20。结果表明检索是主要提升来源，角色分解和用户历史评论进一步改善跨轮次交互质量，视觉信息可能带来文本评估未捕捉的收益。
正文节选
Personalization Matters: Long-Horizon Conversation Agent with User-Centric Information in Online Shopping Interactions Abstract Personalized conversational shopping requires maintaining preference consistency over multi-turn interactions, where users reveal constraints gradually. Existing approaches often rely on static profiles and do not explicitly control long-horizon interaction behavior. We propose a multi-agent, multimodal Retrieval-Augmented Generation (RAG) framework that decomposes dial