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.

翻译：[translated abstract in Chinese] 生成式检索(GR)已成为现代搜索系统中一种前景广阔的新范式。与多阶段级联架构相比，它具有端到端联合优化和高计算效率等优势。作为工业级部署的代表性生成式搜索框架，OneSearch已带来显著的商业和运营效益。然而，其对复杂查询的理解不足、对潜在用户意图的低效挖掘，以及对狭隘历史偏好的过拟合，限制了其性能的进一步提升。为应对这些挑战，我们提出\textbf{OneSearch-V2}——一种潜在推理增强的自蒸馏生成式搜索框架。它包含三项关键创新：(1)思想增强的复杂查询理解模块，实现深度查询理解，克服直接推理的浅层语义匹配局限性；(2)推理内化的自蒸馏训练流程，通过隐式上下文学习，挖掘日志拟合之外的潜在但精准的电商意图；(3)行为偏好对齐优化系统，缓解单一转化指标引发的奖励黑客问题，并通过直接用户反馈处理个性化偏好。大量离线评估证明了OneSearch-V2强大的查询识别和用户画像能力。在线A/B测试进一步验证其业务有效性，实现了商品点击率+3.98%、买家转化率+3.05%和订单量+2.11%的提升。人工评估进一步证实了搜索体验质量的改进，页面优秀率提升+1.65%，查询-商品相关性提升+1.37%。更重要的是，OneSearch-V2有效缓解了信息茧房和长尾稀疏性等常见搜索系统问题，且未增加额外推理成本或服务延迟。