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

2026-06-30

AI Summary

This work addresses the semantic gap in existing intelligent shopping systems between understanding complex user intents and executing precise product operations, which hinders effective handling of multi-turn, ambiguous, or composite requests. To bridge this gap, we propose ShopX—the first end-to-end shopping fulfillment framework that unifies intent understanding, execution planning, and product manipulation within a single foundation model. Its core innovation is the introduction of Semantic IDs (SIDs), enabling native support for product generation, retrieval, ranking, and composition directly within large language models. We further design a tailored training mechanism that preserves general instruction-following capabilities while enabling flexible interaction within the product space. Experiments on real-world Taobao logs demonstrate that ShopX significantly outperforms tool-augmented agents in both single- and multi-turn tasks, achieving higher fulfillment success rates and superior behavioral performance, particularly on complex or ambiguous user requests.

Abstract

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.

Problem

• intent-to-item fulfillment
• agentic shopping
• foundation model
• semantic IDs
• item-space operations

Innovation

• Foundation Model
• Semantic ID (SID)
• Agentic Shopping
• Intent-to-Item Fulfillment
• Model-Native Execution