analiza aiqbench
This paper introduces AIGB-R1, a framework that leverages Large Language Models for generative auto-bidding by separating high-level strategy planning from fine-grained execution. By integrating an experience-driven self-evolving loop and proposing Decoupled Group Relative Policy Optimization (D-GRPO), the system addresses common LLM limitations like hallucinations in numerical tasks to optimize advertising bids autonomously. The research demonstrates a novel application of reasoning-capable AI models within specific machine learning optimization pipelines for commercial decision-making.
AIGB-R1: Self-Evolving Generative Auto-Bidding via Hierarchical Planner-Executor Optimization
arXiv:2607.17281v1 Announce Type: cross 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.
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.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2607.17281 [cs.LG]
(or arXiv:2607.17281v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2607.17281 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 291 cuvinte
Subiecte conexe
Beyond Single-Episode Optimization: Sliding-Window Aware Generative Auto-Bidding for Long-Term Advertising Effectiveness
arXiv · 29 iul. 2026
Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information
arXiv · 26 aug. 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · 27 aug. 2026
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · 13 oct. 2026