OneBid：面向多样化oCPX广告场景的统一自动出价基础模型
OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios
- Kuaishou Technology（快手科技）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
OneBid提出统一自动出价基础模型，通过双信号条件化、序列级MoE和CROP离线优化，在快手oCPX广告中实现整体+2.2%、ROAS场景+13.1%的ADVV提升。
AI中文摘要：
自动出价是计算广告的核心，其策略必须在经济约束下最大化广告主的转化价值。自动出价已从基于规则的控制器演变为强化学习和生成式方法（如决策Transformer，DT）。然而，这些方法日益与主流的优化每行动成本（oCPX）范式不匹配，该范式涵盖异构场景（如注册、购买），每个场景由独立模型服务，导致流水线碎片化且跨场景建模探索不足。受LLM等基础模型的启发，将这些oCPX场景统一到一个模型中面临三个挑战：多目标控制、严格延迟下的可扩展容量，以及安全的离线策略改进。我们提出OneBid，一个统一的自动出价基础模型，它从异构oCPX日志中学习可复用主干，并通过离线后训练将其适配到特定场景部署。基于DT，OneBid将单一返回目标（Return-to-Go）条件扩展为两个原子信号：用于转化价值的返回目标和用于成本比率的成本目标（Cost-to-Go），并在下一动作预测上加入价值感知正则化。为吸收分布异构性，我们设计了序列级混合专家（MoE）架构，其中共享专家编码跨场景知识，稀疏路由专家以低延迟捕获场景特定模式，从而随模型大小和数据实现一致扩展。在后训练阶段，我们通过评论家引导的相对离线策略优化（CROP）将主干与场景偏好对齐：学习到的评论家对候选动作进行组相对评分，避免GRPO风格微调的不安全在线探索，同时约束策略偏移以降低分布外（OOD）风险。通过在线A/B测试验证并已在快手全面部署，OneBid在oCPX广告上整体提升+2.2%的ADVV，在ROAS场景中峰值提升+13.1%。
英文摘要：
Auto-bidding is central to computational advertising, where strategies must maximize advertisers' conversion value under economic constraints. It has evolved from rule-based controllers to reinforcement learning and generative methods such as Decision Transformer (DT). Yet these methods increasingly mismatch the prevailing optimized cost-per-X (oCPX) paradigm, which spans heterogeneous scenarios (e.g., registration, purchase), each served by a separate model, leading to fragmented pipelines and underexploring cross-scenario modeling. Inspired by foundation models like LLMs, unifying these oCPX scenarios into one model raises three challenges: multi-objective control, scalable capacity under strict latency, and safe offline policy improvement. We present OneBid, a unified auto-bidding foundation model that learns a reusable backbone from heterogeneous oCPX logs and adapts it to scenario-specific deployments via offline post-training. Building on DT, OneBid extends single Return-to-Go conditioning to two atomic signals, Return-to-Go for conversion value and Cost-to-Go for cost ratio, plus value-aware regularization on next-action prediction. To absorb distributional heterogeneity, we design a sequence-level Mixture-of-Experts architecture, where shared experts encode cross-scenario knowledge and sparsely-routed experts capture scenario-specific patterns at low latency, yielding consistent scaling with model size and data. During post-training, we align the backbone with scenario preferences via Critic-guided Relative Offline Policy optimization (CROP): a learned critic scores candidate actions group-relatively, avoiding the unsafe online exploration of GRPO-style fine-tuning while constraining policy shift to reduce OOD risk. Validated via online A/B tests and fully deployed at Kuaishou, OneBid delivers an overall +2.2% ADVV gain on oCPX Ads, peaking at +13.1% in the ROAS scenario.
