REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimization
Not on the map. Why?
Abstract (arXiv)
In Taobao e-commerce visual search, user behavior analysis reveals a large proportion of no-click requests, suggesting diverse and implicit user intents. These intents are expressed in various forms and are difficult to mine and discover, thereby leading to the limited adaptability and lag in platform strategies. This greatly restricts users' ability to express diverse intents and hinders the scalability of the visual search system. This mismatch between user implicit intent expression and system response defines the User-SearchSys Intent Discrepancy. To alleviate the issue, we propose a novel framework REVISION. This framework integrates offline reasoning mining with online decision-making and execution, enabling adaptive strategies to solve implicit user demands. In the offline stage, we construct a periodic pipeline to mine discrepancies from historical no-click requests. Leveraging large models, we analyze implicit intent factors and infer optimal suggestions by jointly reasoning over query and product metadata. These inferred suggestions serve as actionable insights for refining platform strategies. In the online stage, REVISION-R1-3B, trained on the curated offline data, performs holistic analysis over query images and associated historical products to generate optimization plans and adaptively schedule strategies across the search pipeline. Our framework offers a streamlined paradigm for integrating large models with traditional search systems, enabling end-to-end intelligent optimization across information aggregation and user interaction. Experimental results demonstrate that our approach improves the efficiency of implicit intent mining from large-scale search logs and significantly reduces the no-click rate.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 39 of its 55 references that are in the map. First posted on arXiv 26 Oct 2025.
Builds on
39 of 55 references.
References · 39
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
- 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
- 2025Qwen3 Technical Reportcited by 8,195
- 2025Qwen2.5-VL Technical Reportcited by 5,418
- 2024GPT-4o System Cardcited by 4,467
- 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
- 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
- 2014CIDEr: Consensus-based Image Description Evaluationcited by 2,027
- 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,107
- 2024DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Servingcited by 595
- 2024Large Language Models: A Surveycited by 506
27 more
- 2025Seed1.5-VL Technical Reportcited by 367
- 2023Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Followingcited by 192
- 2023Query2doc: Query Expansion with Large Language Modelscited by 146
- 2023ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidancecited by 70
- 2024Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agentcited by 65
- 2025PaSa: An LLM Agent for Comprehensive Academic Paper Searchcited by 61
- 2025Plan-Then-Execute: An Empirical Study of User Trust and Team Performance When Using LLM Agents As A Daily Assistantcited by 54
- 2023Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Modelscited by 42
- 2024A Multi-Agent Conversational Recommender Systemcited by 42
- 2022Efficiently Leveraging Multi-level User Intent for Session-based Recommendation via Atten-Mixer Networkcited by 38
- 2024Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrievalcited by 31
- 2022New Intent Discovery with Pre-training and Contrastive Learningcited by 28
- 2021Visual Search at Alibabacited by 27
- 2024BASES: Large-scale Web Search User Simulation with Large Language Model based Agentscited by 24
- 2024Doing Personal LAPS: LLM-Augmented Dialogue Construction for Personalized Multi-Session Conversational Searchcited by 24
- 2024Any2Point: Empowering Any-modality Large Models for Efficient 3D Understandingcited by 23
- 2025Towards AI Search Paradigmcited by 19
- 2025LLM2Rec: Large Language Models Are Powerful Embedding Models for Sequential Recommendationcited by 19
- 2025Exploring the Potential of Encoder-free Architectures in 3D LMMscited by 16
- 2023IPDreamer: Appearance-Controllable 3D Object Generation with Complex Image Promptscited by 11
- 2024GenRewrite: Query Rewriting via Large Language Modelscited by 11
- 2024MIND: Multimodal Shopping Intention Distillation from Large Vision-language Models for E-commerce Purchase Understandingcited by 10
- 2024Semantic Score Distillation Sampling for Compositional Text-to-3D Generationcited by 9
- 2022Graph Enhanced BERT for Query Understandingcited by 3
- 2025AutoMat: Enabling Automated Crystal Structure Reconstruction from Microscopy via Agentic Tool Usecited by 3
- 2024From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classificationcited by 2
- 2024Intent-guided Heterogeneous Graph Contrastive Learning for Recommendationcited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.