ShopX: A Foundation Model for Intent-to-Item Fulfillment in Agentic Shopping

Source

Source name: arXiv
Source kind: paper
Authors / organization: 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
Venue: arXiv: cs.IR
Published: 2026-06-30
Collected: 2026-07-01
URL: http://arxiv.org/abs/2606.31693v1
PDF: https://arxiv.org/pdf/2606.31693v1
DOI: UNKNOWN

Plain-Language Brief

The paper proposes ShopX, a foundation model aimed at bridging the gap between language understanding and item-space fulfillment in AI shopping applications. It unifies intent understanding, execution planning, and flexible SID-native item-space operations into a single model. The model is designed to work within an agentic shopping framework that reduces hand-offs between agent orchestration and item-space execution.

What the Document Says

The AI-native shopping applications are transitioning from page/feed browsing to intent-driven experiences orchestrated by LLM agents.
A common design wraps an LLM around existing search and recommendation pipelines, but complex intents are forced through low-bandwidth retrieval interfaces.
Generative recommendation provides LLMs with a direct item-space interface, but existing models mainly generate candidates for retrieval rather than translating flexible intents into item-space outcomes.
The proposed ShopX model aims to address this bottleneck by unifying intent understanding, execution planning, and flexible SID-native item-space operations.
ShopX is deployed in agentic shopping workflows through a model-native item-fulfillment framework.
Within this framework, ShopX plans and composes SID-based item-space operations such as SID beam-search retrieval, listwise ranking, or product bundling.
The paper describes the design of semantically recoverable, LLM-operable SIDs and a training recipe for ShopX.
The evaluation of ShopX shows improvements in overall framework behavior on complex or ambiguous requests compared to tool-mediated agentic systems.

Key Concepts Mentioned

AI-native applications
LLM agents
intent-driven experiences
ShopX
SIDs
generative recommendation
semantic IDs
intent understanding
execution planning
item-space operations
agentic shopping workflows
model-native item-fulfillment framework
SID beam-search retrieval
listwise ranking
product bundling
training recipe

Claims Made by the Document

AI-native applications are moving beyond page/feed browsing.
Existing designs wrap an LLM around existing search and recommendation pipelines but have complex intents forced through low-bandwidth interfaces.
Generative recommendation provides LLMs a direct item-space interface, but existing models mainly generate candidates for retrieval rather than translating flexible intents into item-space outcomes.
ShopX addresses the bottleneck by unifying intent understanding, execution planning, and flexible SID-native item-space operations.
ShopX improves overall framework behavior on complex or ambiguous requests compared to tool-mediated agentic systems.

Evidence Used

The text describes the wave of AI-native applications moving shopping beyond page/feed browsing
The text mentions the common design wrapping an LLM around existing search and recommendation pipelines
The text states that generative recommendation provides LLMs a direct item-space interface, but existing models mainly generate candidates for retrieval rather than translating flexible intents
The paper proposes ShopX to address this bottleneck by unifying intent understanding, execution planning, and flexible SID-native item-space operations
The text mentions that the evaluation of ShopX shows improvements in overall framework behavior on complex or ambiguous requests compared to tool-mediated agentic systems.

Methods / Approach

UNKNOWN

Limitations Stated by the Authors

UNKNOWN

Limitations Noted by the Agent

Agent interpretation — not from the source.

UNKNOWN

Open Questions

UNKNOWN

Notes for Future Q&A

May include interpretation. Labeled where it does.

UNKNOWN

Raw Abstract / Excerpt

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.