# AdMuse: Skill-Guided Creative Advertising Image Generation

**Authors:** Minyan Luo, Yuxin Zhang, Meng Zhao, Xincan Wang, Fuzhang Wu, Tong-Yee Lee, Oliver Deussen, Fan Tang, Weiming Dong  
**Lab:** Institute of Automation · **Published:** 29 Oct 2026  
**Links:** [arXiv](https://arxiv.org/abs/2610.40190) · [PDF](https://arxiv.org/pdf/2610.40190) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2610.40190.html)

## Abstract

An outstanding creative advertising image should both attract attention and communicate a product's positioning. How to choose a persuasive conceptual bridge before rendering begins is challenging for advertising generation. We present AdMuse, a skill-guided multi-agent framework that distills high-quality advertisements into reusable creative skills for cross-domain advertising strategy. Rather than retrieving isolated exemplars, AdMuse abstracts recurring bridge patterns into a skill library that can guide new product briefs. At generation time, AdMuse coordinates skill routing, multi-candidate ideation and selection, and VLM-guided visual refinement: diverse skills propose alternative concepts, relative judgment selects the most promising direction, and vision-language feedback helps realize the selected intent in the final image. This design treats advertising creativity as a structured decision process rather than a single prompt-writing step. Experiments across diverse product and brand positionings show that AdMuse produces visually compelling advertisements that faithfully communicate product positioning.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.