Strategy-Aware Parameter-Efficient Adaptation for LLM-based Auto-Bidding

2026-07-27

AI Summary

This work addresses the limitations of existing large language model–based automated bidding methods, which suffer from shallow trajectory–text interactions and the high computational cost of full-parameter fine-tuning, hindering effective exploitation of pretrained knowledge in multi-constraint scenarios. To overcome these challenges, we propose SAGE, a framework featuring position enhancement, textual alignment, and constraint-gated LoRA modules that enable policy-aware multimodal alignment with parameter-efficient adaptation. Specifically, SAGE incorporates temporal–semantic positional encoding, gated cross-attention mechanisms, and a sparse mixture-of-experts activation strategy routed by constraint signals, significantly enhancing multimodal fusion while reducing computational overhead. Experiments demonstrate that SAGE substantially outperforms state-of-the-art approaches on large-scale automated bidding benchmarks, achieving superior performance with fewer than 10% of trainable parameters.

Abstract

Advertising bidding has evolved from manual strategies to auto-bidding systems better adapted for large-scale, dynamic auction environments. While recent advances in Large Language Models (LLMs) offer strong reasoning for auto-bidding, existing methods suffer from shallow trajectory-text interactions and require costly fine-tuning, hindering the efficient use of pretrained knowledge under diverse constraints. To address these challenges, we propose SAGE, a novel Strategy-aware Auto-bidding framework Guided by LLMs for Efficient bidding. SAGE introduces a parameter-efficient multi-modal alignment framework for constrained auto-bidding with LLMs. Specifically, SAGE comprises three key components: (i) the position augmentation module adopts temporal-semantic positional embeddings to effectively capture the intrinsic dynamics and semantic structures; (ii) the text alignment module leverages gated cross-attention to align the embedding spaces of trajectory and text modalities, enabling effective multi-modal fusion while alleviating the computational overhead caused by long trajectories; (iii) the constraint-gated LoRA module employs constraints as routing signals, activating only a small subset of experts to adapt the behavior of a frozen LLM efficiently. Extensive experiments on large-scale auto-bidding benchmark demonstrate that SAGE consistently achieves superior performance while tuning less than 10% of the trainable parameters required by full fine-tuning. Ablation studies further validate the critical contribution of each component to the framework's overall performance.

Problem

• auto-bidding
• large language models
• parameter-efficient adaptation
• multi-modal alignment
• constrained optimization

Innovation

• parameter-efficient adaptation
• multi-modal alignment
• constrained auto-bidding
• gated cross-attention
• constraint-gated LoRA