# Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Advertising Effectiveness

arXiv: https://arxiv.org/abs/2607.25233 · HTML: https://mlsanity.com/paper/2607.25233/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 45 references that are in the map.
- First posted on arXiv 28 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [Offline Reinforcement Learning with Implicit Q-Learning](https://mlsanity.com/paper/2110.06169/) (2021)
- [Off-Policy Deep Reinforcement Learning without Exploration](https://mlsanity.com/paper/1812.02900/) (2018)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Offline Reinforcement Learning as One Big Sequence Modeling Problem](https://mlsanity.com/paper/2106.02039/) (2021)
- [Online Convex Optimization with Stochastic Constraints](https://mlsanity.com/paper/1708.03741/) (2017)
- [Real-Time Bidding by Reinforcement Learning in Display Advertising](https://mlsanity.com/paper/1701.02490/) (2017)
- [Optimized Cost per Click in Taobao Display Advertising](https://mlsanity.com/paper/1703.02091/) (2017)
- [Masked Trajectory Models for Prediction, Representation, and Control](https://mlsanity.com/paper/2305.02968/) (2023)
- [Deep Reinforcement Learning for Sponsored Search Real-time Bidding](https://mlsanity.com/paper/1803.00259/) (2018)
- [Sustainable Online Reinforcement Learning for Auto-bidding](https://mlsanity.com/paper/2210.07006/) (2022)
- [AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games](https://mlsanity.com/paper/2412.10798/) (2024)
- [Generative Auto-Bidding with Value-Guided Explorations](https://mlsanity.com/paper/2504.14587/) (2025)
- [Robust Auction Design in the Auto-bidding World](https://mlsanity.com/paper/2111.02468/) (2021)
- [Towards Efficient Auctions in an Auto-bidding World](https://mlsanity.com/paper/2103.13356/) (2021)
- [Multi-channel Autobidding with Budget and ROI Constraints](https://mlsanity.com/paper/2302.01523/) (2023)
- [Offline Reinforcement Learning for Optimizing Production Bidding Policies](https://mlsanity.com/paper/2310.09426/) (2023)
- [Learning Versatile Skills with Curriculum Masking](https://mlsanity.com/paper/2410.17744/) (2024)
- [PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Bidding](https://mlsanity.com/paper/2602.08261/) (2026)

## Abstract (arXiv)

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.