mlsanityData to 14 Oct 2026

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

arXiv 2606.31693 ↗First posted 30 Jun 2026cs.IR cs.AI cs.CLcited by 0

On the map: LLM agents and tool use → Social simulation and multi-agent debate

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Social simulation and multi-agent debate, one of 16 directions in LLM agents and tool use. Builds on 42 of its 82 references that are in the map. First posted on arXiv 30 Jun 2026.

Builds on

42 of 82 references.

References · 42

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  3. 2025Qwen3 Technical Reportcited by 8,820
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2021Program Synthesis with Large Language Modelscited by 3,637
  7. 2025Qwen3-VL Technical Reportcited by 2,793
  8. 2023G-Eval: NLG Evaluation using GPT-4 with Better Human Alignmentcited by 2,276
  9. 2023Instruction-Following Evaluation for Large Language Modelscited by 1,228
  10. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,160
  11. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  12. 2023Enhancing Chat Language Models by Scaling High-quality Instructional Conversationscited by 839
30 more
  1. 2023A Survey on Large Language Models for Recommendationcited by 379
  2. 2025SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Modelcited by 335
  3. 2026Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipecited by 299
  4. 2023Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender Systemcited by 242
  5. 2026MiMo-V2-Flash Technical Reportcited by 191
  6. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendationscited by 131
  7. 2025Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Librarycited by 101
  8. 2023Zero-Shot Listwise Document Reranking with a Large Language Modelcited by 82
  9. 2026Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillationcited by 60
  10. 2025OneRec-Think: In-Text Reasoning for Generative Recommendationcited by 51
  11. 2024COIG-CQIA: Quality is All You Need for Chinese Instruction Fine-tuningcited by 45
  12. 2024LLM4Rerank: LLM-based Auto-Reranking Framework for Recommendationscited by 40
  13. 2025MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interactioncited by 39
  14. 2025Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Datasetcited by 38
  15. 2026Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameterscited by 36
  16. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrievalcited by 33
  17. 2025OneRec-V2 Technical Reportcited by 29
  18. 2025OneRec Technical Reportcited by 25
  19. 2025OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Searchcited by 25
  20. 2024RecAI: Leveraging Large Language Models for Next-Generation Recommender Systemscited by 20
  21. 2025FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasetscited by 17
  22. 2025OpenOneRec Technical Reportcited by 16
  23. 2015Improved Residual Vector Quantization for High-dimensional Approximate Nearest Neighbor Searchcited by 11
  24. 2025RecGPT Technical Reportcited by 11
  25. 2025LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendationcited by 10
  26. 2025RecGPT-V2 Technical Reportcited by 8
  27. 2025Universal Item Tokenization for Transferable Generative Recommendationcited by 7
  28. 2024Towards noise contrastive estimation with soft targets for conditional modelscited by 5
  29. 2025BBQRec: Behavior-Bind Quantization for Multi-Modal Sequential Recommendationcited by 5
  30. 2025Improving Conversational Recommendation with Contextual Adaptation of External Recommenders and LLM-based Rerankingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026AgenticShop: Benchmarking Agentic Product Curation for Personalized Web Shopping
  2. 2026Agentic Multi-Source Grounding for Enhanced Query Intent Understanding: A DoorDash Case Study
  3. 2026RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerce
  4. 2025ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents
  5. 2026EComAgentBench: Benchmarking Shopping Agents on Long-Horizon Tasks with Distributed Hidden Intent
  6. 2026Improving Item Discoverability in e-Commerce Search via Related Intent Generation
  7. 2026ShopSimulator: Evaluating and Exploring RL-Driven LLM Agent for Shopping Assistants
  8. 2026ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation