针对长期广告效果评估，提出滑动窗口感知的生成式自动出价框架。
Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Advertising Effectiveness
- 分层设计：先规划后执行，用掩码轨迹模型预测市场并生成候选策略。
- 在7天滑动窗口下实现稳定约束满足，线上实验提升广告价值获取。
- 适合需长期效果评估的广告平台，尤其对低频高价值投放场景有效。
自动出价系统在效率约束（如每行动成本，CPA）下优化出价以最大化价值。现有方法将每天视为独立决策周期，但许多广告主的价值产生极为稀疏，导致单日效率比统计不可靠，影响广告主留存。因此平台改用7天滑动窗口评估窗口级效率，确保公平性与长期有效性。这引入了跨周期耦合：每日出价决策影响最多W=7个重叠窗口，需预判未来市场状况设定目标。本文提出SWAG-Bid（滑动窗口感知生成式自动出价），采用分层架构，将问题分解为周期级规划与步骤级执行。规划器使用掩码轨迹模型预测市场并生成候选计划，通过多窗口模型预测控制采样（MWMS）结合指数置信衰减，在所有重叠窗口中评分。控制器通过状态自适应门控机制（PSG-AdaLN）动态调整对规划引导的依赖，辅以返现值（Return-to-Go）和成本至终点（Cost-to-Go）通道传递预算与约束信息。在AuctionNet-Sparse数据集及阿里速卖通线上A/B测试中，SWAG-Bid在滑动窗口评估下实现了竞争力的约束满足率与价值获取能力。
原文摘要 · Abstract (English)
Auto-bidding systems optimize bids to maximize value under efficiency constraints such as Cost-Per-Action (CPA). Existing methods treat each day as an independent episode. However, many advertisers produce value so sparsely that per-day efficiency ratios become statistically unreliable, undermining advertiser retention. Platforms therefore evaluate window-level efficiency over sliding windows of $W{=}7$ days, ensuring fair evaluation and long-term advertising effectiveness. This creates cross-episode coupling: each day's bidding decisions affect up to $W$ overlapping windows, so setting daily targets requires anticipating future market conditions. We propose SWAG-Bid (Sliding-Window Aware Generative Auto-Bidding), a hierarchical framework decomposing this challenge into episode-level planning and step-level execution. The planner uses a Masked Trajectory Model to forecast markets and generate candidate plans, scored across all overlapping windows by Multi-Window Model Predictive Control Sampling (MWMS) with exponential confidence decay. The controller adjusts reliance on this guidance through a state-adaptive gate, Per-Step Gated Adaptive Layer Normalization (PSG-AdaLN), complemented by Return-to-Go and Cost-to-Go channels carrying budget and constraint information. Experiments on AuctionNet-Sparse and online A/B tests on AliExpress show that SWAG-Bid achieves competitive constraint satisfaction and value acquisition under sliding-window evaluation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。