AI 中文总结
该研究针对电商目录动态变化问题，提出与商家无关的多轮对话购物助手，核心为自刷新检索器，仅处理目录增量，对话层用LLM做意图分类，演示为WhatsApp购物助手。
AI 中文摘要
基于大语言模型（LLM）的对话推荐系统通常在静态、预索引的商品集合上进行评估，但电商目录会因商品的添加、移除、重新定价和补货而持续变化。我们提出一种与商家无关的多轮对话购物助手，可在这类动态目录上运行。其核心组件是自刷新检索器，它会接入商家商品信息流，丰富记录并将其同步到向量索引中。每次运行时，每个商品的哈希值可识别出哪些商品是新的、已变更、已删除或未变更，因此仅处理增量部分，无需重建整个目录。基于控制器的对话层会使用该索引，仅将LLM用于意图分类和偏好引导，而检索、重排序和多样性选择则作为专用函数运行。我们的演示是WhatsApp购物助手，目录变更会在下一次成功同步后反馈到推荐中。相关实时聊天机器人、文档和录制的演示可在该https URL获取。
英文摘要
Conversational recommender systems based on large language models (LLMs) are usually evaluated on static, pre-indexed item collections, yet e-commerce catalogues change continuously as products are added or removed, repriced, and restocked. We present a merchant-agnostic, multi-turn conversational shopping assistant that operates over such live catalogues. Its central component is a self-refreshing retriever that ingests a merchant product feed, enriches the records, and synchronizes them into a vector index. On each run, per-item hashes identify which products are new, changed, deleted, or unchanged, so only the delta is processed rather than rebuilding the whole catalogue. A controller-based dialogue layer consumes this index, using an LLM only for intent classification and preference elicitation while retrieval, reranking, and diversity selection run as dedicated functions. Our demonstration is a WhatsApp shopping assistant in which catalogue changes reach the recommendations after the next successful sync. A live chatbot, documentation, and a recorded walkthrough are available at https://github.com/infobip/infobip-agentic-crs.
CommentsACM RecSys 2026, 3 pages, 2 figure, 1 table
