OneSearch-V2: The Latent Reasoning Enhanced Self-distillation Generative Search Framework

2026-03-25

AI Summary

This work proposes a generative search framework that integrates implicit reasoning and self-distillation to address key limitations in existing systems, including inadequate comprehension of complex queries, insufficient user intent modeling, and overfitting to historical preferences. The framework features a chain-of-thought–enhanced query understanding module, a self-distillation training mechanism with internalized reasoning, and a behavior-based preference alignment strategy leveraging user feedback to achieve more accurate intent capture and result generation. Online A/B experiments demonstrate significant improvements in product click-through rate (+3.98%), buyer conversion rate (+3.05%), and order volume (+2.11%). Furthermore, the approach enhances search relevance and page-level user experience while effectively mitigating filter bubbles and long-tail sparsity issues.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions

Abstract

Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems. Compared to multi-stage cascaded architecture, it offers advantages such as end-to-end joint optimization and high computational efficiency. OneSearch, as a representative industrial-scale deployed generative search framework, has brought significant commercial and operational benefits. However, its inadequate understanding of complex queries, inefficient exploitation of latent user intents, and overfitting to narrow historical preferences have limited its further performance improvement. To address these challenges, we propose \textbf{OneSearch-V2}, a latent reasoning enhanced self-distillation generative search framework. It contains three key innovations: (1) a thought-augmented complex query understanding module, which enables deep query understanding and overcomes the shallow semantic matching limitations of direct inference; (2) a reasoning-internalized self-distillation training pipeline, which uncovers users' potential yet precise e-commerce intentions beyond log-fitting through implicit in-context learning; (3) a behavior preference alignment optimization system, which mitigates reward hacking arising from the single conversion metric, and addresses personal preference via direct user feedback. Extensive offline evaluations demonstrate OneSearch-V2's strong query recognition and user profiling capabilities. Online A/B tests further validate its business effectiveness, yielding +3.98\% item CTR, +3.05\% buyer conversion rate, and +2.11\% order volume. Manual evaluation further confirms gains in search experience quality, with +1.65\% in page good rate and +1.37\% in query-item relevance. More importantly, OneSearch-V2 effectively mitigates common search system issues such as information bubbles and long-tail sparsity, without incurring additional inference costs or serving latency.

Problem

• Generative Retrieval
• complex query understanding
• latent user intent
• overfitting to historical preferences
• information bubbles

Innovation

• Generative Retrieval
• Latent Reasoning
• Self-distillation
• Query Understanding
• Preference Alignment