arXiv cs.AI· Chenyu Mu, Wenming Weng, Qinrui Wang, Xingsong Ye, Hao Yu, Jun He, Chong Sun, Chen Li, Jing Lyu, Erkun Yang, Cheng Deng·· 14 小时前AI 评分52
WeVisCut：用一个智能体完成从旁白到长视频的完整剪辑
WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video
AI 导读
WeVisCut 是一个从脚本到长视频的生成系统，把工具执行与策略学习接在同一智能体框架内，用共享制作状态让工具反馈影响后续决策与修复。作者用编辑反演加验证回放的四阶段数据管线处理 3,750 条成片，得到超过 130K 训练样本，并训练单个 9B 策略模型。
正文 · 原文
Authors:Chenyu Mu, Wenming Weng, Qinrui Wang, Xingsong Ye, Hao Yu, Jun He, Chong Sun, Chen Li, Jing Lyu, Erkun Yang, Cheng Deng
Abstract:Producing long-form videos from narration requires interdependent decisions that remain coherent across shots. Existing agentic editors often use multi-stage workflows driven by general models, leaving the quality-cost trade-off of compact, task-adapted policies unclear. We address this gap with WeVisCut, a long-form script-to-video system that connects tool execution with policy learning. Its agent harness maintains shared production state so that tool feedback informs subsequent decisions and repairs. Because finished videos do not expose these decisions, our four-stage data pipeline combines editing inversion with verified replay to turn recovered editing intent into executable supervision. Applied to 3,750 finished videos, this pipeline yields over 130K training examples. We use this supervision to train a single 9B policy that coordinates production and recovers from failures within the same harness. Moreover, we introduce a 100-task benchmark and five metrics assessing editing quality and delivery reliability. Under a shared tool environment, WeVisCut substantially outperforms its base model and achieves comparable performance to Claude Opus 5 while using nearly 33x fewer generated tokens per successful output minute. It also outperforms task-matched native editors on our proposed metrics.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.38352 [cs.CV] |
| (or arXiv:2610.38352v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.38352 arXiv-issued DOI via DataCite |
Submission history
From: Chenyu Mu [view email]
[v1]
Wed, 28 Oct 2026 06:51:40 UTC (29,603 KB)
来源：arXiv cs.AI · arxiv.org