ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping
作者: Jiacheng Chen, Tao Zhang, Manxi Lin, Dunxian Huang, Teng Shi, Honghao Fu, Mengyan Li, Xinming Zhang, Chenchi Zhang, Xuan Lu, Xiaoxiong Du, Haibin Chen, Shaolin Ye, Hao Chang, Xiaoqi Li, Shuwen Xiao, Yujin Yuan, Jingxuan Feng, Shaopan Xiong, Huimin Yi, Ju Huang, Qiu Shen, Ying Chen, Junjun Zheng, Xiangheng Kong, Yuning Jiang
分类: cs.IR, cs.AI, cs.CL
发布日期: 2026-06-30
💡 一句话要点
提出ShopX以解决意图驱动购物中的项目履行问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 意图驱动购物 大型语言模型 项目履行 语义ID 多轮交互 智能推荐 电子商务
📋 核心要点
- 现有方法将LLM与搜索推荐结合,导致意图理解与项目履行之间的低带宽瓶颈。
- ShopX通过统一意图理解、执行规划和SID操作,构建单一基础模型以解决这一问题。
- 实验结果表明,ShopX在单轮和多轮履行任务中表现优越,尤其在复杂请求上有显著提升。
📝 摘要(中文)
随着AI原生应用的发展,购物体验正从基于页面和信息流的浏览转向由大型语言模型(LLM)代理驱动的意图驱动体验。现有设计将LLM与搜索和推荐管道结合,导致意图理解与项目履行之间存在差距。为了解决这一瓶颈,本文提出了ShopX,通过统一意图理解、执行规划和灵活的语义ID(SID)操作,构建一个基础模型。ShopX在代理购物工作流中部署,提供模型原生的项目履行框架,显著提升了复杂或模糊请求的处理能力。
🔬 方法详解
问题定义:本文旨在解决意图驱动购物中,现有方法在意图理解与项目履行之间的低带宽问题。现有模型主要生成候选项,而非将灵活的意图转化为具体的项目结果。
核心思路:论文提出ShopX,通过将意图理解、执行规划和SID操作统一为一个基础模型,直接在项目空间中进行操作,减少了代理协调与项目执行之间的损失性交接。
技术框架:ShopX的整体架构包括意图理解模块、执行规划模块和SID操作模块。该框架定义了模型面向的动作协议,并提供上下文访问、目录基础和状态管理的支持。
关键创新:ShopX的主要创新在于设计了可语义恢复的、可操作的SID,并提出了一种训练方案,使得通用LLM能够灵活地进行多轮项目履行,同时保留购物代理所需的知识和指令跟随能力。
关键设计:在关键设计方面,ShopX采用了SID束搜索检索、列表排名和产品捆绑等操作,确保模型能够高效地处理复杂请求。
🖼️ 关键图片
📊 实验亮点
在与工具中介的代理系统进行对比实验中,ShopX在单轮和多轮履行任务上表现出色,尤其在处理复杂或模糊请求时,整体框架行为显著改善,提升幅度明显。
🎯 应用场景
ShopX的研究成果可广泛应用于电子商务平台、智能购物助手和个性化推荐系统等领域。通过提升意图理解和项目履行的效率,ShopX能够为用户提供更为流畅和个性化的购物体验,推动未来智能购物的发展。
📄 摘要(原文)
The wave of AI-native applications is moving shopping beyond page- and feed-based browsing toward intent-driven experiences orchestrated by LLM agents. A common design wraps an LLM around existing search and recommendation pipelines, forcing complex intents through low-bandwidth retrieval or ranking interfaces and leaving a gap between language understanding and item-space fulfillment. Generative recommendation gives LLMs a direct item-space interface through semantic IDs (SIDs), but existing models mainly generate candidates for retrieval rather than translate flexible intents into item-space outcomes. We propose ShopX to address this bottleneck by unifying intent understanding, execution planning, and flexible SID-native item-space operations into a single foundation model. We deploy ShopX in agentic shopping workflows through a model-native item-fulfillment framework with a serving harness that defines a model-facing action protocol and exposes support surfaces for context access, catalog grounding, and state management. Within this framework, ShopX plans and composes SID-based item-space operations such as SID beam-search retrieval, listwise ranking, or product bundling. This model-centric design reduces lossy hand-offs between agent orchestration and item-space execution. To build ShopX, we design semantically recoverable, LLM-operable SIDs and a training recipe that equips a general LLM for flexible multi-turn item-space fulfillment while retaining the knowledge and instruction-following abilities needed by a shopping agent. We evaluate the ShopX framework against tool-mediated agentic systems on single- and multi-turn fulfillment tasks derived from anonymized Taobao production logs, showing that model-native fulfillment improves overall framework behavior, especially on complex or ambiguous requests.