AIGQ: An End-to-End Hybrid Generative Architecture for E-commerce Query Recommendation

2026-03-20

AI Summary

Traditional e-commerce query suggestion methods rely on ID matching and co-click heuristics, suffering from shallow semantic understanding, poor cold-start performance, and low serendipity. This work proposes AIGQ—the first end-to-end generative query recommendation framework tailored for the HintQ scenario—introducing two key innovations: Interest-aware List-wise Supervised Fine-Tuning (IL-SFT) and List-wise Group Relative Policy Optimization (IL-GRPO). Furthermore, AIGQ employs a hybrid offline-online deployment architecture that integrates nearline generation (AIGQ-Direct) with trigger-word reasoning augmentation (AIGQ-Think). Large-scale experiments on the Taobao platform demonstrate that AIGQ significantly improves core metrics including platform efficiency and user engagement.

Technology Category

• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Intelligent Query Processing
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Pre-search query recommendation, widely known as HintQ on Taobao's homepage, plays a vital role in intent capture and demand discovery, yet traditional methods suffer from shallow semantics, poor cold-start performance and low serendipity due to reliance on ID-based matching and co-click heuristics. To overcome these challenges, we propose AIGQ (AI-Generated Query architecture), the first end-to-end generative framework for HintQ scenario. AIGQ is built upon three core innovations spanning training paradigm, policy optimization and deployment architecture. First, we propose Interest-Aware List Supervised Fine-Tuning (IL-SFT), a list-level supervised learning approach that constructs training samples through session-aware behavior aggregation and interest-guided re-ranking strategy to faithfully model nuanced user intent. Accordingly, we design Interest-aware List Group Relative Policy Optimization (IL-GRPO), a novel policy gradient algorithm with a dual-component reward mechanism that jointly optimizes individual query relevance and global list properties, enhanced by a model-based reward from the online click-through rate (CTR) ranking model. To deploy under strict real-time and low-latency requirements, we further develop a hybrid offline-online architecture comprising AIGQ-Direct for nearline personalized user-to-query generation and AIGQ-Think, a reasoning-enhanced variant that produces trigger-to-query mappings to enrich interest diversity. Extensive offline evaluations and large-scale online A/B experiments on Taobao demonstrate that AIGQ consistently delivers substantial improvements in key business metrics across platform effectiveness and user engagement.

Problem

• query recommendation
• cold-start
• shallow semantics
• serendipity
• e-commerce

Innovation

• generative query recommendation
• list-level supervised fine-tuning
• policy optimization
• hybrid offline-online architecture
• interest-aware modeling