SEGB: Self-Evolved Generative Bidding with Local Autoregressive Diffusion

TL;DR

SEGB introduces a self-evolving, offline reinforcement learning framework for online ad bidding that synthesizes future states and refines policies without external data, significantly improving performance and business value.

Contribution

The paper presents SEGB, a novel offline planning and self-evolution framework for generative bidding that enhances policy effectiveness without external simulation or expert input.

Findings

Outperforms state-of-the-art baselines on AuctionNet benchmark

Achieves +10.19% increase in target cost in large-scale deployment

Demonstrates robust policy improvement solely from static data

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 Generative Bidding (SEGB), 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.