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 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, +2.07\% buyer volume, and +2.11\% order volume. Manual evaluation further confirms gains in search experience quality, with +1.37\% in page good rate and +1.65\% 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（Generative Retrieval, GR）已成为现代搜索系统中一种有前景的范式。与多级级联架构相比，它具备端到端联合优化和高计算效率等优势。OneSearch作为代表性的大规模工业部署生成式搜索框架，已带来显著的商业与运营效益。然而，其存在的复杂查询理解不足、潜在用户意图挖掘效率低下以及过度拟合狭窄历史偏好等问题，限制了性能的进一步提升。为解决这些挑战，我们提出了OneSearch-V2——一种增强潜在推理的自蒸馏生成搜索框架。它包含三项关键创新：（1）思维增强型复杂查询理解模块，可实现对查询的深度理解，克服直接推理在浅层语义匹配上的局限性；（2）推理内化式自蒸馏训练流程，通过隐式上下文学习挖掘用户超越日志拟合的潜在精准电商意图；（3）行为偏好对齐优化系统，缓解由单一转化指标导致的奖励黑客问题，并通过直接用户反馈处理个性化偏好。大量离线评估表明，OneSearch-V2具备强大的查询识别与用户画像能力。在线A/B测试进一步验证了其业务有效性，商品点击率提升+3.98%，买家数提升+2.07%，订单量提升+2.11%。人工评估也证实了搜索体验质量的提升，页面优质率提高+1.37%，查询-商品相关性提高+1.65%。更重要的是，OneSearch-V2有效缓解了常见搜索系统中的信息茧房和长尾稀疏问题，且未增加额外推理成本或服务延迟。