Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-Editing
cs.CV, cs.CL
Submitted: 2026-08-26
Updated: 2026-08-26
Comments: Accepted to the Main Conference of EMNLP '26
License: http://creativecommons.org/licenses/by/4.0/
The gist: Practical video editing is not only pixel generation: an editor must turn a brief, a clip pool, music metadata, and hard constraints into an executable timeline.
Terminology
Abstract
Practical video editing is not only pixel generation: an editor must turn a brief, a clip pool, music metadata, and hard constraints into an executable timeline. We study this decision layer as executable video-editing planning and introduce RefineCut, which, unlike workflow systems that wrap a prompted frontier model, trains a compact open-weight planner for it. The planner edits a typed timeline through structured patches covering clip selection, trimming, ordering, transitions, and duration and music alignment; a deterministic verifier applies each patch and checks it against an explicit constraint ledger. Because editing has no single ground-truth repair, we do not imitate teachers directly: RefineCut replays every multi-teacher branch through the verifier and keeps verifier-best repairs as supervision. A second stage, RefineCut-Evo, lets the student score its own repairs with the verifier and a task rubric and trains on high-margin preference pairs, so the final 8 B planner runs in a closed verifier loop with no teacher calls at inference. On RefineCut-Bench (3, 578 tasks, 7, 971 captioned clips, 499 music tracks, explicit ledgers), verifier-replayed distillation lifts the planner from 0.620 to 0.858 on the protocol-specific Video-Editing Score and RefineCut-Evo reaches 0.924; the gain transfers to Llama-3.1-8B and GLM-4-9B, and in the same closed loop the 8 B planner matches or exceeds its frontier teachers. Code and RefineCut-Bench are publicly released; see the Data Availability statement.
Sources
- Rubric-Grounded RL: Structured Judge Rewards for Generalizable Reasoning
- Training Verifiers to Solve Math Word Problems
- StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration
- HunyuanVideo: A Systematic Framework For Large Video Generative Models
- DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing
- EvoLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics
- UniVA: Universal Video Agent towards Open-Source Next-Generation Video Generalist
- GLANCE: A Global-Local Coordination Multi-Agent Framework for Music-Grounded Non-Linear Video Editing
- Uniform-Correct Policy Optimization: Breaking RLVR's Indifference to Diversity
- Movie Gen: A Cast of Media Foundation Models
- Wan: Open and Advanced Large-Scale Video Generative Models
- Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution
- Instruction-Following Evaluation for Large Language Models
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models