mlsanityData to 7 Oct 2026

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

arXiv 2607.25233 ↗First posted 28 Jul 2026cs.LGcited by 0

Not on the map. Why?

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 45 references that are in the map. First posted on arXiv 28 Jul 2026.

Builds on

23 of 45 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017FiLM: Visual Reasoning with a General Conditioning Layercited by 2,286
  3. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  4. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  5. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
  6. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
  7. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  8. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  9. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  10. 2017Online Convex Optimization with Stochastic Constraintscited by 94
  11. 2017Real-Time Bidding by Reinforcement Learning in Display Advertisingcited by 90
  12. 2017Optimized Cost per Click in Taobao Display Advertisingcited by 57
11 more
  1. 2023Masked Trajectory Models for Prediction, Representation, and Controlcited by 40
  2. 2018Deep Reinforcement Learning for Sponsored Search Real-time Biddingcited by 34
  3. 2022Sustainable Online Reinforcement Learning for Auto-biddingcited by 28
  4. 2024AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Gamescited by 26
  5. 2025Generative Auto-Bidding with Value-Guided Explorationscited by 23
  6. 2021Robust Auction Design in the Auto-bidding Worldcited by 21
  7. 2021Towards Efficient Auctions in an Auto-bidding Worldcited by 19
  8. 2023Multi-channel Autobidding with Budget and ROI Constraintscited by 14
  9. 2023Offline Reinforcement Learning for Optimizing Production Bidding Policiescited by 8
  10. 2024Learning Versatile Skills with Curriculum Maskingcited by 2
  11. 2026PRO-Bid: Pareto-Prioritized Regret Optimization for Constraint-Aware Generative Auto-Biddingcited by 1

Built on by

Not cited yet.