Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning
Summary
This paper introduces an agentic framework combining LLMs and VLMs for consistent multi-instruction video editing across multiple shots, and proposes the MMLVE task and benchmark to evaluate performance.
View Cached Full Text
Cached at: 08/28/26, 07:24 AM
Paper page - Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning
Source: https://huggingface.co/papers/2608.26809 Published on Aug 27
·
Submitted byhttps://huggingface.co/FireCRT
Fuchenon Aug 28
Abstract
An agentic framework combining LLMs and VLMs enables consistent, multi-instruction editing of long multi-shot videos while preserving spatiotemporal structure.
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 theMulti-Instruction Multi-Shot Long-Video Editing(MMLVE) task, which is structured around three core objectives:Cross-Shot Editing Consistency(CSEC),Multi-Instruction Decoupling(MID), andZero-Destruction on Spatiotemporal Structure(ZDSS). To tackle these three unique challenges, we introduce an agentic editing framework that leverages the synergy ofLarge Language Models(LLMs) andVision-Language Models(VLMs) to achieve shot-level video decoupling and precise instruction parsing. Furthermore, to comprehensively evaluate this task, we constructMMLVE-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, preservingcross-shot editing consistency, and attaining seamless spatiotemporal transitions.
View arXiv pageView PDFProject pageGitHub2Add to collection
Get this paper in your agent:
hf papers read 2608\.26809
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.26809 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.26809 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.26809 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
ThinkV2V: Unleashing the Reasoning Capability of MLLMs for Instruction-Guided Video Editing
ThinkV2V introduces a reasoning-driven framework that activates MLLM thinking before visual generation for instruction-guided video editing, using an MLLM-to-DiT architecture with progressive curriculum training and inference-time thinking scaling. The authors also release the ThinkV2V-150K dataset and ThinkV2V-Bench, showing their 5B DiT model outperforms larger 10B baselines.
VideoMM: Adaptive Macro-Micro Inference for Efficient Video MLLMs
VideoMM introduces an adaptive macro-micro inference framework that reduces visual token overhead in video MLLMs, achieving a 6.13× speedup and 7.4% accuracy gain for efficient long-form video understanding.
VLX-VR: An Agentic-Aware Video Reasoning Model
VLX-VR is an agentic-aware video reasoning model that uses a Think–Memory–Observation loop and reinforcement learning to adaptively gather evidence, achieving state-of-the-art performance on the MINERVA benchmark.
Watch, Remember, Reason: Human-View Video Understanding with MLLMs
A survey presenting a human-view perspective on video understanding with multimodal large language models, organized around watching, remembering, and reasoning abilities, covering challenges, methods, and applications.
Collaborative Memory for Multi-Agent VLM Systems
This paper proposes a collaborative memory framework for multi-agent vision-language model systems to address distributed perception and improve shared visual context and reasoning consistency.