WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video
WeVisCut: The Whole Editing Room in One Agent From Narration to Long-Form Video
WeVisCut coordinates video editing tools, recovers from failures, and reduces token usage through a compact strategy trained on 9B parameters, while maintaining output quality. The system employs a four-stage data pipeline, combining editing inversion and validation replay, to generate over 130K training examples from 3,750 finished videos for training a single strategy.
Published on Oct 28
Authors:
,
,
,
,
,
,
,
,
Abstract
WeVisCut is a script-to-video system that trains a compact policy to coordinate video editing tools, recover from failures, and reduce token usage while maintaining quality.
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.
View arXiv page View PDF Project page GitHub 38 Add to collection
Get this paper in your agent:
hf papers read 2610.38352
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Any-to-Any • 9B • Updated 3 days ago • 191 • 20tencent/WeVisCut
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2610.38352 in a dataset README.md to link it from this page.
Spaces citing this paper 7
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.
Source: Hugging Face Daily Papers · huggingface.co