cs.CVNov 17, 2026

CutAgent: Creative-Gene-Driven Planning and Experience-Guided Self-Refinement for High-CTR E-commerce Advertising Video Creation

Authors: Xuyue Huang, Guanbo Huang, Jiasong Feng, Run Ling, Ao Ma, Xi Zhao, Yaoyu Li, Jie Gao, 

Organizations: Tsinghua University · Tianjin University · Zhejiang University

Abstract

E-commerce advertising video creation requires both high-level creative planning and reliable multi-modal production. However, existing methods often map product attributes directly to scripts or editing decisions without explicitly modeling advertising strategies, narrative structures, and production styles. They also have limited ability to reuse past production failures. To address these limitations, we propose CutAgent\textbf{CutAgent}, a dual-agent framework that formulates advertising video creation as a Plan--Execute--Self-Evolve process. CutAgent comprises two collaborative agents, GeneAgent\textbf{GeneAgent} and VideoAgent\textbf{VideoAgent}, connected by a structured creative gene that bridges product understanding and video production. GeneAgent maps multi-modal product inputs---textual attributes together with product images---to creative genes that specify narrative units and production rules. To train GeneAgent, we construct CutAgent-70K\textbf{CutAgent-70K} with approximately 70K samples of product attributes/images, reverse-extracted creative genes, cleaned clip pools, and real-world CTR, and apply high-CTR supervised fine-tuning followed by CTR-guided GRPO. Guided by the generated gene, VideoAgent retrieves category-then-gene failure--correction experiences from a long-term memory as constraints for shot-script planning, then coordinates material retrieval, narration, subtitles, music, and timeline rendering. Independently, a reflection loop diagnoses quality defects, revises deficient production decisions, and writes verified corrections back to memory for later retrieval. Experiments on CutAgent-Eval\textbf{CutAgent-Eval} show that CutAgent outperforms representative baselines in e-commerce advertising video creation, achieving the highest online CTR of 2.21%\textbf{2.21\%}.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AgenticGen: Reward-Guided Agentic Video Generation for Advertising

    Aug 31, 2026Xingyuan Bu, Chengru Song, Hao Zhou +9Reward ModelingAgentic RL

  2. KD-CVG: A Knowledge-Driven Approach for Creative Video Generation

    Apr 23, 2026Linkai Liu, Wei Feng, Xi Zhao +9Multimodal RAGT2V Generation