← 研踪 PaperTrailarXiv:2611.22418 · v1
CutAgent: Creative-Gene-Driven Planning and Experience-Guided Self-Refinement for High-CTR E-commerce Advertising Video Creation
首次提交 2026-11-17 16:54
版本更新 2026-11-17 16:54
雷达观测 2026-11-18 19:42
摘要
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 , a dual-agent framework that formulates advertising video creation as a Plan--Execute--Self-Evolve process. CutAgent comprises two collaborative agents, and , 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 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 show that CutAgent outperforms representative baselines in e-commerce advertising video creation, achieving the highest online CTR of .
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-17 16:54 · 最新观测版本
CutAgent: Creative-Gene-Driven Planning and Experience-Guided Self-Refinement for High-CTR E-commerce Advertising Video Creation
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 , a dual-agent framework that formulates advertising video creation as a Plan--Execute--Self-Evolve process. CutAgent comprises two collaborative agents, and , 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 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 show that CutAgent outperforms representative baselines in e-commerce advertising video creation, achieving the highest online CTR of .
查看此版本解读 →查看此版本原文 ↗