LBM: Hierarchical Large Auto-Bidding Model via Reasoning and Acting
#LBM #auto-bidding #hierarchical model #reasoning #acting #advertising #AI #auctions
📌 Key Takeaways
- LBM is a hierarchical auto-bidding model designed for automated ad bidding.
- It integrates reasoning and acting to optimize bidding strategies.
- The model aims to improve efficiency and performance in digital advertising auctions.
- It represents an advancement in AI-driven advertising technology.
📖 Full Retelling
arXiv:2603.05134v1 Announce Type: cross
Abstract: The growing scale of ad auctions on online advertising platforms has intensified competition, making manual bidding impractical and necessitating auto-bidding to help advertisers achieve their economic goals. Current auto-bidding methods have evolved to use offline reinforcement learning or generative methods to optimize bidding strategies, but they can sometimes behave counterintuitively due to the black-box training manner and limited mode cov
🏷️ Themes
AI Advertising, Automated Bidding
📚 Related People & Topics
Artificial intelligence
Intelligence of machines
# Artificial Intelligence (AI) **Artificial Intelligence (AI)** is a specialized field of computer science dedicated to the development and study of computational systems capable of performing tasks typically associated with human intelligence. These tasks include learning, reasoning, problem-solvi...
Entity Intersection Graph
No entity connections available yet for this article.
Mentioned Entities
Original Source
--> Computer Science > Computation and Language arXiv:2603.05134 [Submitted on 5 Mar 2026] Title: LBM: Hierarchical Large Auto-Bidding Model via Reasoning and Acting Authors: Yewen Li , Zhiyi Lyu , Peng Jiang , Qingpeng Cai , Fei Pan , Bo An , Peng Jiang View a PDF of the paper titled LBM: Hierarchical Large Auto-Bidding Model via Reasoning and Acting, by Yewen Li and 6 other authors View PDF HTML Abstract: The growing scale of ad auctions on online advertising platforms has intensified competition, making manual bidding impractical and necessitating auto-bidding to help advertisers achieve their economic goals. Current auto-bidding methods have evolved to use offline reinforcement learning or generative methods to optimize bidding strategies, but they can sometimes behave counterintuitively due to the black-box training manner and limited mode coverage of datasets, leading to challenges in understanding task status and generalization in dynamic ad environments. Large language models offer a promising solution by leveraging prior human knowledge and reasoning abilities to improve auto-bidding performance. However, directly applying LLMs to auto-bidding faces difficulties due to the need for precise actions in competitive auctions and the lack of specialized auto-bidding knowledge, which can lead to hallucinations and suboptimal decisions. To address these challenges, we propose a hierarchical Large autoBidding Model to leverage the reasoning capabilities of LLMs for developing a superior auto-bidding strategy. This includes a high-level LBM-Think model for reasoning and a low-level LBM-Act model for action generation. Specifically, we propose a dual embedding mechanism to efficiently fuse two modalities, including language and numerical inputs, for language-guided training of the LBM-Act; then, we propose an offline reinforcement fine-tuning technique termed GQPO for mitigating the LLM-Think's hallucinations and enhancing decision-making performance without simulati...
Read full article at source