cs.LGSep 18, 2026

OneBid: A Unified Auto-Bidding Foundation Model for Diverse oCPX Advertising Scenarios

Authors: Yewen Li, Peng Jiang, Yitian Li, Pengfei Lv, Xialong Liu, Peng Jiang, Qingpeng Cai

Organizations: Kuaishou Technology Beijing, China

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Auto-bidding is central to computational advertising, where strategies must maximize advertisers' conversion value under economic constraints. It has evolved from rule-based controllers to reinforcement learning and generative methods such as Decision Transformer (DT). Yet these methods increasingly mismatch the prevailing optimized cost-per-X (oCPX) paradigm, which spans heterogeneous scenarios (e.g., registration, purchase), each served by a separate model, leading to fragmented pipelines and underexploring cross-scenario modeling. Inspired by foundation models like LLMs, unifying these oCPX scenarios into one model raises three challenges: multi-objective control, scalable capacity under strict latency, and safe offline policy improvement. We present OneBid, a unified auto-bidding foundation model that learns a reusable backbone from heterogeneous oCPX logs and adapts it to scenario-specific deployments via offline post-training. Building on DT, OneBid extends single Return-to-Go conditioning to two atomic signals, Return-to-Go for conversion value and Cost-to-Go for cost ratio, plus value-aware regularization on next-action prediction. To absorb distributional heterogeneity, we design a sequence-level Mixture-of-Experts architecture, where shared experts encode cross-scenario knowledge and sparsely-routed experts capture scenario-specific patterns at low latency, yielding consistent scaling with model size and data. During post-training, we align the backbone with scenario preferences via Critic-guided Relative Offline Policy optimization (CROP): a learned critic scores candidate actions group-relatively, avoiding the unsafe online exploration of GRPO-style fine-tuning while constraining policy shift to reduce OOD risk. Validated via online A/B tests and fully deployed at Kuaishou, OneBid delivers an overall +2.2% ADVV gain on oCPX Ads, peaking at +13.1% in the ROAS scenario.

Figures & tables

Figure 1. Overview of OneBid. (I) Pre-training: Heterogeneous oCPX logs are organized into unified bidding trajectories, each tokenized with state, action, task/scenario identity, and two control signals—Return-to-Go (RTG) for conversion value demand and Cost-to-Go (CTG) for cost-efficiency control. Inside each Transformer block, the Sequence-Level Mixture-of-Experts (S-MoE) module combines always-on shared experts, which encode cross-scenario regularities, with task-routed experts, which capture scenario-specific residual dynamics while keeping activated computation fixed for low-latency serving. Training combines next-action prediction with auxiliary Q/V value prediction, so the backbone imitates logged bids while encoding long-horizon value prediction. (II) Post-training: Deployment-specific preferences are instantiated through a controllable reward system and critic learning, followed by CROP, a Critic-guided Relative Offline Policy optimization method that improves the actor using offline candidate actions while limiting policy shift. (III) Deployment: The resulting policy is integrated into the production auto-bidding system, where offline improvement and online serving form a closed deployment pipeline.
Figure 2. Pretraining scaling behavior of OneBid. The held-out NAP loss consistently decreases as either model size or pretraining data volume increases.
Figure 3. Offline ablations of key pretraining components. (a) CTG ablation. (b) S-MoE capacity scaling compared with the Dense architecture.
Figure 4. Critic scaling behavior in post-training. Held-out Q regression error decreases as critic model size and data volume increases.
MetricAWRGASCROP
ΔQ/Qlabel\Delta Q/Q_{\mathrm{label}} ↑\uparrow0.12%0.06%1.90%
Table 1. Q-value improvement of fine-tuning methods.
ComparisonADVV ↑\uparrowValid Ratio ↑\uparrow
IQL vs MPC+1.4%-0.1pp
DT vs IQL+4.0%+1.0pp
Pretrained OneBid vs DT+1.0% CI: [0.1%, 1.8%]+1.7pp
Finetuned OneBid vs DT+1.9% CI: [1.0%, 2.8%]+2.8pp
Table 2. Online A/B gains across successive generations of auto-bidding methods (MPC → IQL → DT → Pretrained OneBid → Finetuned OneBid) in the oCPX Form Submit scenario. Each row reports the gain of a method over its immediate predecessor. CI denotes the confidence interval.
MethodModel SizeLatency (ms)
DT (baseline)10M40ms
OneBid60M52ms
Table 3. Online serving latency comparison.
ScenarioADVV ↑\uparrowValid Ratio ↑\uparrow
Purchase+2.5% CI: [0.7%, 4.3%]+4.1pp
ROAS+13.1% CI: [5.0%, 28%]+3.1pp
Activation+1.8% CI: [1.3%, 2.2%]−- 0.3pp
Form Submit+1.9% CI: [1.0%,2.8%]+2.8pp
Leads Submit+2.3% CI: [1.1%, 3.7%]+0.5pp
oCPX Overall+2.2%—
Table 4. Cumulative online A/B test gains of OneBid across major oCPX scenarios, where CI denotes confidence interval.
Figure 5. T-SNE visualization of OneBid’s shared and scenario-specific representations across transformer depths. Each point corresponds to the representation of a sampled bidding sequence and is colored by its oCPX scenario. Shared-expert outputs are largely intermixed across scenarios, indicating reusable cross-scenario bidding knowledge, while routed-expert outputs form more scenario-aligned clusters, reflecting scenario-specific residual information learned within the unified OneBid backbone.
Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 6. CROP training curves. CROP improves Q values while keeping KL stable, indicating effective offline policy improvement without policy collapse.
ImplementationLatency (ms)Peak Memory (MB)
Token-level MoE22.18±0.1122.18\pm 0.11389.6389.6
S-MoE (ours)1.71±0.03\mathbf{1.71\pm 0.03}232.1\mathbf{232.1}
Appendix
Table 5. Latency and memory comparison of MoE implementations with 256 experts, measured on a single NVIDIA H800 GPU (batch size 32, sequence length 20, hidden dim 128, top- k=2k=2 ). S-MoE achieves over 13×13\times lower latency and ∼\sim 40%40\% lower peak memory than token-level MoE.
More in this topic

Automated Bidding

Automated bidding studies algorithms that choose auction bids over time while balancing value, budgets, and performance constraints.

See all 37 papers

Explore similar work

CardsList
Jul 29, 2026

PlatformBid: An Auto-Bidding Benchmark from a Unified Advertising Platform's Perspective

Real-time bidding is central to computational advertising, comprising three elements: Supply Side Platform (SSP) selling ad impressions, Demand Side Platform (DSP) bidding for advertisers, and Ad Exchange conducting auctions between them. Traditional auto-bidding algorithms focus solely on the DSP side, maximizing advertiser conversions by adjusting bids against competitors. However, current big ad platforms, such as social media and e-commerce companies, now integrate SSP, DSP, and Ad Exchange functions internally. From such ad platforms' perspective, the goal of the auto-bidding algorithms is not only to maximize the advertisers' conversions, but also the total revenue of the platform. Given the lack of platform-centric evaluation frameworks and the pressing need to advance auto-bidding research, we propose PlatformBid - the first comprehensive benchmark designed from a unified ad platform's perspective. To accurately reflect the real-world auto-bidding scenarios, we define three representative settings: (1) homogeneous competition with identical algorithms across advertisers, (2) heterogeneous competition with diverse algorithmic strategies, and (3) promotional competition where some advertisers surge budgets for boosting sales during promotional events like Black Friday. We systematically evaluate a broad spectrum of existing auto-bidding methods across these settings, encompassing classical control methods, RL-based methods, and recent generative methods. Besides these methods, we further propose a novel auto-bidding method based on flow-matching, termed BidFlow, which leverages the flow-matching method's expressive policy representation to effectively handle dynamic competitive environments. Online experiments on Kuaishou further show a +0.68% improvement in target cost, providing deployment evidence for the offline-online consistency of PlatformBid.

Shengtian Yang, Yewen Li, Peng Jiang +5

Nanyang Technological University Singapore, Singapore

Benchmark DesignAutomated BiddingOnline AdvertisingReal-Time Bidding
AskPDF
Apr 7, 2026

JD-BP: A Joint-Decision Generative Framework for Auto-Bidding and Pricing

Auto-bidding services optimize real-time bidding strategies for advertisers under key performance indicator (KPI) constraints such as target return on investment and budget. However, uncertainties such as model prediction errors and feedback latency can cause bidding strategies to deviate from ex-post optimality, leading to inefficient allocation. To address this issue, we propose JD-BP, a Joint generative Decision framework for Bidding and Pricing. Unlike prior methods, JD-BP jointly outputs a bid value and a pricing correction term that acts additively with the payment rule such as GSP. To mitigate adverse effects of historical constraint violations, we design a memory-less Return-to-Go that encourages future value maximizing of bidding actions while the cumulated bias is handled by the pricing correction. Moreover, a trajectory augmentation algorithm is proposed to generate joint bidding-pricing trajectories from a (possibly arbitrary) base bidding policy, enabling efficient plug-and-play deployment of our algorithm from existing RL/generative bidding models. Finally, we employ an Energy-Based Direct Preference Optimization method in conjunction with a cross-attention module to enhance the joint learning performance of bidding and pricing correction. Offline experiments on the AuctionNet dataset demonstrate that JD-BP achieves state-of-the-art performance. Online A/B tests at JD.com confirm its practical effectiveness, showing a 4.70% increase in ad revenue and a 6.48% improvement in target cost.

Linghui Meng, Chun Gan, Shengsheng Niu +8

JD.com China · The Chinese University of Hong Kong China

Automated BiddingReal-Time BiddingOnline AdvertisingDynamic Pricing
AskPDF
Jun 12, 2026

DRIVE: Distributional and Retrieval-Augmented Bidding with Value Evaluation

Auto-bidding is a core component of real-time advertising systems, where decisions must optimize long-term performance under budget and cost constraints, while online exploration is prohibitively risky. Offline reinforcement learning and, more recently, Transformer-based sequence modeling have shown promise for learning bidding policies from logged data, but their unimodal and purely parametric formulations often collapse multiple effective bidding strategies into suboptimal averaged actions and perform unreliably under sparse or long-tail traffic. To mitigate these limitations, we propose DRIVE (Distributional and Retrieval-Augmented Bidding with Value Evaluation), a unified Transformer-based framework that decouples candidate action generation from decision making for offline auto-bidding. DRIVE combines distributional action modeling, retrieval-augmented candidate generation from high-quality historical decisions, and value-based evaluation to select the most promising bid at inference time. Extensive experiments on AuctionNet and additional offline reinforcement learning benchmarks demonstrate that DRIVE consistently improves bidding performance and generalizes well across multiple Transformer-based methods.

Miduo Cui, Haochen Wang, Shangqin Mao +6

Shandong University, Jinan, China · Meituan, Beijing, China

Distributional RLAutomated BiddingOffline RLReal-Time Bidding
AskPDF