Long conversation shopping agent improves personalized user experience online
Personalization Matters: Long-Horizon Conversation Agent with User-Centric Information in Online Shopping Interactions
Multiagent Systems
Summary
Buying things online with a chat assistant can be tricky when you share your preferences bit by bit over many messages. The authors propose a system that splits the task into parts like tracking your preferences, searching products, reasoning based on your history and product info, and then responding to you. Their system uses product details, reviews, images, and what you’ve said before to better understand you. Tests show their method keeps preferences consistent over long chats and users rate it higher for personalization.
What this means in practice
- •For e-commerce developers: Build chat shopping assistants that maintain user preferences consistently over long buying conversations using multimodal information.$Commercial implications: Enables improved personalized shopping assistants that can be sold as customer service tools for online retailers.
- •For customer support engineers: Create chatbots that better manage multi-turn user constraints and product data to provide consistent, personalized support.
Authors
Rena Gao, Yue Dai, Hao Guan, Shengxiang Gao, Wangyang Wu, Yixin Shen, Jey Han Lau
Abstract
Personalized conversational shopping requires maintaining preference consistency over multi-turn interactions, where users reveal constraints gradually. Existing approaches often rely on static profiles and do not explicitly control long-horizon interaction behavior. We propose a multi-agent, multimodal Retrieval-Augmented Generation (RAG) framework that decomposes dialogue state tracking, recommendation retrieval, preference-aware reasoning, and response generation, while integrating product metadata, product reviews, image-derived descriptions, and user historical reviews. To evaluate interaction-level quality, we adopt a trajectory-level protocol with four dimensions: Global Preference Consistency, Cumulative Information Synthesis, Interaction Trajectory, and Tone Consistency. On an Amazon Reviews 2023 benchmark, retrieval-enabled variants outperform a no-RAG baseline on automatic trajectory metrics (average 4.82 vs. 3.74). In a small real-user study ($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: https://github.com/RenaGao/Multimodel_RAG_Indexing