Paper Detail

Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning

Chenyang Wu, Fuchen Long, Binyuan Huang, Xinlong Sun, Xi Chen, Chun-Le Guo, Chongyi Li

huggingface Score 15.5

Published 2026-08-27 · First seen 2026-08-28

General AI

Abstract

While generative AI has significantly advanced video editing, existing methods primarily focus on single-shot or short video clips. Editing long videos with multiple instructions remains a formidable challenge. Naive chunking strategies, e.g., fixed-duration segmentation, often lead to entity fragmentation, severe editing hallucinations, and disrupted temporal continuity. To bridge this gap, we introduce the Multi-Instruction Multi-Shot Long-Video Editing (MMLVE) task, which is structured around three core objectives: Cross-Shot Editing Consistency (CSEC), Multi-Instruction Decoupling (MID), and Zero-Destruction on Spatiotemporal Structure (ZDSS). To tackle these three unique challenges, we introduce an agentic editing framework that leverages the synergy of Large Language Models (LLMs) and Vision-Language Models (VLMs) to achieve shot-level video decoupling and precise instruction parsing. Furthermore, to comprehensively evaluate this task, we construct MMLVE-Bench, which is an MMLVE-focused dataset characterized by complex real-world spatiotemporal dynamics, high-density heterogeneous instructions, and sparse, random entity distributions. Three MMLVE-focused evaluation metrics are further exploited to assess the quality of the editing results. Extensive experiments demonstrate that our MMLVE-Agent outperforms existing closed-source SOTA approaches (e.g., Seedance 2.0), successfully eliminating editing hallucinations, preserving cross-shot editing consistency, and attaining seamless spatiotemporal transitions.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{wu2026thinking,
  title = {Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning},
  author = {Chenyang Wu and Fuchen Long and Binyuan Huang and Xinlong Sun and Xi Chen and Chun-Le Guo and Chongyi Li},
  year = {2026},
  abstract = {While generative AI has significantly advanced video editing, existing methods primarily focus on single-shot or short video clips. Editing long videos with multiple instructions remains a formidable challenge. Naive chunking strategies, e.g., fixed-duration segmentation, often lead to entity fragmentation, severe editing hallucinations, and disrupted temporal continuity. To bridge this gap, we introduce the Multi-Instruction Multi-Shot Long-Video Editing (MMLVE) task, which is structured around},
  url = {https://huggingface.co/papers/2608.26809},
  keywords = {Multi-Instruction Multi-Shot Long-Video Editing, Cross-Shot Editing Consistency, Multi-Instruction Decoupling, Zero-Destruction on Spatiotemporal Structure, Large Language Models, Vision-Language Models, MMLVE-Bench, code available, huggingface daily},
  eprint = {2608.26809},
  archiveprefix = {arXiv},
}

Metadata

{}