LEAPS: An LLM-Empowered Adaptive Plugin for Taobao AI Search

2026-01-09

arXiv.org

AI Summary

This work addresses the challenge that traditional e-commerce search systems struggle to effectively handle high-dimensional, conversational queries powered by large language models, often resulting in zero-result responses or information overload. The authors propose an “Expand-and-Refine” paradigm that integrates non-intrusive, adaptive plugins at both ends of the search pipeline: an upstream Query Expander employs a three-stage training strategy combined with diversity-aware reinforcement learning to generate complementary queries and broaden recall, while a downstream Relevance Verifier leverages multi-source signals—such as OCR-extracted text and user reviews—along with chain-of-thought reasoning to precisely filter noise, augmented by semantic gating to mitigate choice overload. The architecture is fully compatible with existing short-text retrieval systems and enables low-cost deployment. Both offline evaluations and online A/B tests demonstrate significant improvements in search experience, leading to its full-scale deployment in Taobao’s AI-powered search system as of August 2025, serving hundreds of millions of users monthly.

Technology Category

• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Constraint Satisfaction and Optimization: Search

Application Category

• Search and Retrieval-Augmented AI: Ad search and search for Web retail
• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The rapid advancement of large language models has reshaped user search cognition, driving a paradigm shift from discrete keyword-based search to high-dimensional conversational interaction. However, existing e-commerce search architectures face a critical capability deficit in adapting to this change. Users are often caught in a dilemma: precise natural language descriptions frequently trigger zero-result scenarios, while the forced simplification of queries leads to decision overload from noisy, generic results. To tackle this challenge, we propose LEAPS (LLM-Empowered Adaptive Plugin for Taobao AI Search), which seamlessly upgrades traditional search systems via a"Broaden-and-Refine"paradigm. Specifically, it attaches plugins to both ends of the search pipeline: (1) Upstream, a Query Expander acts as an intent translator. It employs a novel three-stage training strategy--inverse data augmentation, posterior-knowledge supervised fine-tuning, and diversity-aware reinforcement learning--to generate adaptive and complementary query combinations that maximize the candidate product set. (2) Downstream, a Relevance Verifier serves as a semantic gatekeeper. By synthesizing multi-source data (e.g., OCR text, reviews) and leveraging chain-of-thought reasoning, it precisely filters noise to resolve selection overload. Extensive offline experiments and online A/B testing demonstrate that LEAPS significantly enhances conversational search experiences. Crucially, its non-invasive architecture preserves established retrieval performance optimized for short-text queries, while simultaneously allowing for low-cost integration into diverse back-ends. Fully deployed on Taobao AI Search since August 2025, LEAPS currently serves hundreds of millions of users monthly.

Problem

• conversational search
• e-commerce search
• query understanding
• zero-result problem
• decision overload

Innovation

• LLM-Empowered Search
• Query Expansion
• Relevance Verification
• Conversational E-commerce Search
• Non-invasive Plugin Architecture