用多智能体自动构建零售价格分类体系，解决海量商品定价不一致问题。
Lines and Ladders: A Context-Aware Multi-Agent Framework for Large-Scale Retail Price Taxonomy
- 设计三智能体框架，通过属性识别与分层分组生成价格层级结构。
- 在食品类目中达到90%以上精确率和75%以上召回率，通用品类准确率达80.2%。
- 适用于需要规模化管理商品价格的零售企业，尤其适合复杂品类场景。
维持价格一致性并实施每日低价策略对全球零售商至关重要。然而，当商品目录涵盖数百万活跃商品时，人工管理价格关系已不可行。不同商品变体间的价格不一致会扭曲客户价值感知并导致销售流失。为此，我们提出一种可扩展的、上下文感知的多智能体框架，用于自动化构建“价格线与梯级”分类体系。该框架采用专用大模型智能体，通过识别关键属性、提取多模态数值并应用层次化分组逻辑，构建连贯的价格结构。在真实企业数据上评估并投入生产，我们的三智能体系统在‘价格线’任务中取得0.83的F1分数，优于单智能体基线，有效缓解认知过载。在食品与日用品类别中，系统实现超过90%的精确率和超过75%的召回率；在非结构化的通用商品目录中，分类准确率达到80.2%。
原文摘要 · Abstract (English)
Maintaining price consistency and executing an Every Day Low Price strategy is critical for global retailers. However, with catalogs spanning millions of active items, manual governance of price relationships is infeasible. Inconsistent pricing across item variants distorts customer value perception and cannibalizes sales. To address this, we present a scalable, context-aware Multi-Agent Framework designed to automate the construction of "Lines and Ladders" pricing taxonomies. Our framework employs specialized LLM agents to construct these coherent pricing structures by identifying key attributes, extracting multi-modal values, and applying hierarchical grouping logic. Evaluated on real-world enterprise data and deployed in production, our 3-Agent system achieves an F1-score of 0.83 for Lines, outperforming single-agent baselines by mitigating cognitive overload. The system achieves >90% precision and >75% recall in Food & Consumables, and 80.2% assignment accuracy in the unstructured General Merchandise catalog.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。