arXiv cs.MA· Rena Gao, Yue Dai, Hao Guan, Shengxiang Gao, Wangyang Wu, Yixin Shen, Jey Han Lau·· 9 天前AI 评分24
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
Personalization Matters: Long-Horizon Conversation Agent with User-Centric Information in Online Shopping Interactions
AI 导读
研究者提出一个多智能体、多模态 RAG 框架，将对话状态跟踪、推荐检索、偏好感知推理与回复生成解耦，并融合商品元数据、评论、图像描述和用户历史评论。
正文 · 原文
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 dialogue state tracking, recommendation retrieval, preference-aware reasoning, and response generation, while integrating product metadata, product reviews, image-derived descriptions, and user historical reviews. To evaluate interaction-level quality, we adopt a trajectory-level protocol with four dimensions: Global Preference Consistency, Cumulative Information Synthesis, Interaction Trajectory, and Tone Consistency. On an Amazon Reviews 2023 benchmark, retrieval-enabled variants outperform a no-RAG baseline on automatic trajectory metrics (average 4.82 vs. 3.74). In a small real-user study ($n{=}5$), the Full variant achieves the highest mean overall rating (4.60 vs. 2.20 for Baseline), providing exploratory evidence that role decomposition plus user-centric retrieval improves perceived personalization.\footnote{Code and dataset are available at: this https URL
| Comments: | accepted by AACL-IJCNLP 2026 |
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.11375 [cs.MA] |
| (or arXiv:2610.11375v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.11375 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yue Dai [view email]
[v1]
Thu, 8 Oct 2026 07:07:39 UTC (22,579 KB)
来源：arXiv cs.MA · arxiv.org