OneSearch: A Preliminary Exploration of the Unified End-to-End Generative Framework for E-commerce Search

TL;DR

OneSearch addresses the limitations of traditional e-commerce search by unifying recall, pre-ranking, and ranking into an end-to-end generative framework. It introduces KHQE for robust item encoding, Mu-Seq for rich user behavior modeling, and PARS for adaptive, reward-driven ranking, achieving substantial offline and online gains and reducing OPEX. The approach is validated on real industrial data and deployed across KuaiShou platforms, delivering statistically significant improvements in CTR, buyers, and order volume while increasing Model FLOPs Utilization and lowering computational costs. Overall, OneSearch demonstrates the practicality and impact of industrial-scale end-to-end generative retrieval for e-commerce search, with clear avenues for real-time encoding and multimodal extensions.

Abstract

Traditional e-commerce search systems employ multi-stage cascading architectures (MCA) that progressively filter items through recall, pre-ranking, and ranking stages. While effective at balancing computational efficiency with business conversion, these systems suffer from fragmented computation and optimization objective collisions across stages, which ultimately limit their performance ceiling. To address these, we propose \textbf{OneSearch}, the first industrial-deployed end-to-end generative framework for e-commerce search. This framework introduces three key innovations: (1) a Keyword-enhanced Hierarchical Quantization Encoding (KHQE) module, to preserve both hierarchical semantics and distinctive item attributes while maintaining strong query-item relevance constraints; (2) a multi-view user behavior sequence injection strategy that constructs behavior-driven user IDs and incorporates both explicit short-term and implicit long-term sequences to model user preferences comprehensively; and (3) a Preference-Aware Reward System (PARS) featuring multi-stage supervised fine-tuning and adaptive reward-weighted ranking to capture fine-grained user preferences. Extensive offline evaluations on large-scale industry datasets demonstrate OneSearch's superior performance for high-quality recall and ranking. The rigorous online A/B tests confirm its ability to enhance relevance in the same exposure position, achieving statistically significant improvements: +1.67% item CTR, +2.40% buyer, and +3.22% order volume. Furthermore, OneSearch reduces operational expenditure by 75.40% and improves Model FLOPs Utilization from 3.26% to 27.32%. The system has been successfully deployed across multiple search scenarios in Kuaishou, serving millions of users, generating tens of millions of PVs daily.

Figures (11)

• Figure 1: (a) Our proposed End-to-End generative retrieval framework, (b) the traditional multi-stage cascading architecture in E-commerce search.
• Figure 2: Homepage
• Figure 3: Mall
• Figure 4: Detail Page
• Figure 6: The input and output differences among Recommend, Search/Ads, Query Sug and Bottom Bar.