AIGB-R1: Self-Evolving Generative Auto-Bidding via Hierarchical Planner-Executor Optimization

2026-07-19

AI Summary

This work addresses the limitations of existing AI-based bidding methods, which struggle to discover optimal strategies due to insufficient offline data coverage and weak understanding of task states. To overcome these challenges, the authors propose the AIGB-R1 framework, featuring a hierarchical Planner-Executor architecture: a high-level Planner performs macro-strategy planning, while a low-level Executor makes fine-grained decisions. The framework incorporates a decoupled group relative policy optimization (D-GRPO) algorithm and leverages large language model reasoning capabilities, a two-stage training paradigm—comprising offline pretraining and alignment-aware fine-tuning—and an interactive simulation environment to enable end-to-end self-evolving bidding optimization. Experimental results on large-scale public datasets demonstrate that the proposed approach significantly improves automated bidding performance.

Abstract

Auto-bidding plays an essential role in online advertising, automatically adjusting bids for advertisers to optimize their commercial goals. The emerging AI-Generated Bidding (AIGB) paradigm widely adopts generative modeling to optimize bidding strategies, yet suffers from the limited mode coverage of offline datasets and inadequate task-state understanding, hindering effective exploration of optimal strategies. Large Language Models (LLMs), with prior world knowledge and reasoning capabilities, offer a promising approach to overcome these limitations. However, directly applying LLMs to auto-bidding tasks faces inherent challenges in limited numerical precision, hallucinations, and inference latency. To address these limitations, we propose AIGB-R1, a hierarchical self-evolving auto-bidding framework aiming to enhance AI-Generated Bidding via LLMs' Reasoning capabilities, comprising a high-level Planner module for macro-level strategy planning and a low-level Executor module for fine-grained decision-making. Building upon this, we design an experience-driven self-evolving loop, enabling autonomous strategy exploration and optimization from accumulated experience. We adopt a two-stage pipeline of offline pre-training and post-training alignment, and build an interactive bidding simulation environment for strategy rollout. Furthermore, we propose Decoupled Group Relative Policy Optimization (D-GRPO) to achieve end-to-end optimization via advantage decoupling. Experimental results on a large-scale public dataset demonstrate the effectiveness of AIGB-R1.

Problem

• auto-bidding
• AI-Generated Bidding
• Large Language Models
• strategy exploration
• task-state understanding

Innovation

• Self-Evolving
• Hierarchical Planner-Executor
• AI-Generated Bidding
• Decoupled Group Relative Policy Optimization
• Large Language Models