The rise of AI-native applications is transforming shopping from traditional page and feed browsing to intent-driven experiences orchestrated by Large Language Model (LLM) agents. Current designs typically wrap LLMs around existing search and recommendation pipelines, forcing complex intents through low-bandwidth retrieval or ranking interfaces, creating a gap between language understanding and item-space fulfillment.
Generative recommendation provides LLMs with a direct item-space interface through Semantic IDs (SIDs), but existing models mainly generate candidates for retrieval rather than translating flexible intents into item-space outcomes. To address this bottleneck, we propose ShopX, which unifies intent understanding, execution planning, and flexible SID-native item-space operations into a single foundation model.
We deploy ShopX within agentic shopping workflows through a model-native item-fulfillment framework 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.
Blogger's Review: The introduction of the ShopX model signifies a deep integration of intent understanding and item fulfillment, showcasing the immense potential of LLMs in practical applications. By optimizing item-space operations, ShopX can handle complex requests, significantly enhancing user experience and is poised to lead a new wave of transformation in the e-commerce sector.