Go to ICLR 2026 Workshop AIMS homepageSEGB: SELF-EVOLVED GENERATIVE BIDDING WITH LOCAL AUTOREGRESSIVE DIFFUSION
Keywords: Online Advertising, Auto-bidding, Autoregressive Diffusion Model, Offline Reinforcement Learning
TL;DR: By combining an autoregressive diffusion model for foresight with offline policy evolution, our bidding agent learns superior, simulator-free strategies from fixed datasets.
Abstract: In the realm of online advertising, automated bidding has become a pivotal tool,enabling advertisers to efficiently capture impression opportunities in real-time.Recently, generative auto-bidding has shown significant promise, offering innovative solutions for effective ad optimization. However, existing offline-trained generative policies lack the near-term foresight required for dynamic markets and usually depend on simulators or external experts for post-training improvement. To overcome these critical limitations, we propose Self-Evolved GenerativeBidding (SEGB) 1, a framework that plans proactively and refines itself entirely offline. SEGB first synthesizes plausible short-horizon future states to guide each bid, providing the agent with crucial, dynamic foresight. Crucially, it then performs value-guided policy refinement to iteratively discover superior strategies without any external intervention. This self-contained approach uniquely enables
robust policy improvement from static data alone. Experiments on the AuctionNet benchmark and a large-scale A/B test validate our approach, demonstrating that SEGB significantly outperforms state-of-the-art baselines. In a large-scale online deployment, it delivered substantial business value, achieving a +10.19% increase in target cost, proving the effectiveness of our advanced planning and evolution
paradigm.
Track: Long Paper
Email Sharing: We authorize the sharing of all author emails with Program Chairs.
Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.
Submission Number: 77
Loading