Constraint-Aware Generative Auto-bidding via Pareto-Prioritized Regret Optimization

2026-02-09

AI Summary

This work addresses the challenge that existing automated bidding methods struggle to maximize marketing value under strict efficiency constraints—such as target cost-per-acquisition (CPA)—due to state confounding and over-reliance on imitating historical average behaviors. To overcome these limitations, the authors propose PRO-Bid, a novel framework that decouples constraint satisfaction from utility optimization. PRO-Bid leverages Pareto representation to recover resource awareness, reweights high-performing trajectories, and employs counterfactual regret minimization to actively steer the policy toward the optimal constraint boundary. Built upon the Decision Transformer architecture, the framework integrates Pareto-front reweighting, recursive cost-value contextual modeling, and outcome-predictive guidance into a unified weighted regression objective. Experiments demonstrate that PRO-Bid significantly outperforms current approaches on two public benchmarks and in live A/B tests, achieving state-of-the-art performance in both constraint adherence and marketing value.

Technology Category

• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Learning to Search
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Auto-bidding systems aim to maximize marketing value while satisfying strict efficiency constraints such as Target Cost-Per-Action (CPA). Although Decision Transformers provide powerful sequence modeling capabilities, applying them to this constrained setting encounters two challenges: 1) standard Return-to-Go conditioning causes state aliasing by neglecting the cost dimension, preventing precise resource pacing; and 2) standard regression forces the policy to mimic average historical behaviors, thereby limiting the capacity to optimize performance toward the constraint boundary. To address these challenges, we propose PRO-Bid, a constraint-aware generative auto-bidding framework based on two synergistic mechanisms: 1) Constraint-Decoupled Pareto Representation (CDPR) decomposes global constraints into recursive cost and value contexts to restore resource perception, while reweighting trajectories based on the Pareto frontier to focus on high-efficiency data; and 2) Counterfactual Regret Optimization (CRO) facilitates active improvement by utilizing a global outcome predictor to identify superior counterfactual actions. By treating these high-utility outcomes as weighted regression targets, the model transcends historical averages to approach the optimal constraint boundary. Extensive experiments on two public benchmarks and online A/B tests demonstrate that PRO-Bid achieves superior constraint satisfaction and value acquisition compared to state-of-the-art baselines.

Problem

• auto-bidding
• constraint satisfaction
• Target CPA
• resource pacing
• performance optimization

Innovation

• Constraint-Aware Bidding
• Pareto Representation
• Counterfactual Regret Optimization
• Decision Transformer
• Auto-bidding