Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation

• URL: http://arxiv.org/abs/2609.08275v2
• Date: Mon, 14 Sep 2026 10:16:55 GMT
• Title: Beyond Coherence: Benchmarking Professional Editing-Technique Execution in Multi-Shot Audio-Video Generation
• Abstract summary: CutCraft is the first benchmark for editing-technique execution in multi-shot audio-video generation.<n>We design an agentic editing baseline that decomposes generation into planning, shot-level synthesis, and post-hoc composition.<n>We find unstable shot structures, weak control of transition execution, and sharp degradation on higher-order montage.
• Score: 20.067016616921222
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent multi-shot audio-video generators can produce increasingly coherent and cinematic outputs, but coherence does not imply the ability to execute editing techniques. Professional editing depends on shot structure, transition grammar, audio-video cut relations, and montage, yet existing benchmarks largely rely on proxies such as content quality, synchronization, or physical plausibility, systematically missing whether such editing instructions are actually executed. We introduce CutCraft, the first benchmark for editing-technique execution in multi-shot audio-video generation. CutCraft extends structured multi-shot prompts with explicit editing specifications and is paired with a hierarchical hybrid evaluation framework that combines shot-structure alignment, expert-model metrics, tool-grounded multimodal judgment, and rubric-based question answering. Beyond evaluation, we design an agentic editing baseline that decomposes generation into planning, shot-level synthesis, and post-hoc composition, explicitly realizing editing semantics such as J-cuts, L-cuts, and transition timing. Across 13 state-of-the-art closed- and open-source models, CutCraft reveals a consistent gap between coherence and editing-technique execution: current systems often produce plausible multi-shot videos yet fail to execute editorial instructions reliably. We find unstable shot structures, weak control of transition execution, and sharp degradation on higher-order montage, while aesthetic quality is only weakly correlated with editing-technique compliance. The benchmark and metrics, and the editing agent baseline are available at https://github.com/AlibabaResearch/cut-craft-bench.

Related papers

• Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation [53.27387848819395]
  Long-form narrative-to-film generation requires shot-level controllability and cross-clip consistency.<n>We introduce a structured orchestration layer for film-oriented script-to-video generation.
  arXiv  Detail & Related papers  (2026-09-07T16:33:14Z)
• CoVEBench: Can Video Editing Models Handle Complex Instructions? [26.871333176496126]
  CoVEBench is a compositional video editing benchmark comprising 416 curated source videos, 626 multi-point editing instructions, and 9,990 fine-grained checklist items.<n>It evaluates models via MLLM-judged instruction compliance and video fidelity, alongside automated metrics for video quality.
  arXiv  Detail & Related papers  (2026-06-07T02:29:41Z)
• A Benchmark and Multi-Agent System for Instruction-driven Cinematic Video Compilation [75.66313073019326]
  We introduce CineBench, the first benchmark for instruction-driven cinematic video compilation.<n>We present CineAgents, a multi-agent system that reformulates cinematic video compilation into design-and-compose'' paradigm.
  arXiv  Detail & Related papers  (2026-04-12T04:39:09Z)
• CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator [8.901958956012072]
  Conditional image editing is crucial in scenarios requiring strict structural control.<n>Most approaches rely on single-step generation.<n>We propose textbfCAMEO, a structured multi-agent framework that reformulates conditional editing as a quality-aware, feedback-driven process.
  arXiv  Detail & Related papers  (2026-04-03T16:27:02Z)
• CutClaw: Agentic Hours-Long Video Editing via Music Synchronization [96.62825277039117]
  CutClaw is an autonomous multi-agent framework designed to edit hours-long raw footage into meaningful short videos.<n>It produces videos with synchronized music, followed by instructions, and a visually appealing appearance.<n>We conduct detailed experiments to demonstrate that CutClaw significantly outperforms state-of-the-art baselines in generating high-quality, rhythm-aligned videos.
  arXiv  Detail & Related papers  (2026-03-31T12:25:53Z)
• CoEditor++: Instruction-based Visual Editing via Cognitive Reasoning [98.98349220451216]
  CoEditor++ is a training-free framework that decomposes editing into "what to edit" and "how to edit"<n>We show that CoEditor++ achieves state-of-the-art performance in both general editing and responsible editing tasks.<n>Our findings suggest the potential toward cognitive-centric instruction-based image editing.
  arXiv  Detail & Related papers  (2026-01-31T12:20:46Z)
• FlowDC: Flow-Based Decoupling-Decay for Complex Image Editing [52.54102743380658]
  We propose FlowDC, which decouples the complex editing into multiple sub-editing effects and superposes them in parallel during the editing process.<n>FlowDC shows superior results compared with existing methods.
  arXiv  Detail & Related papers  (2025-12-12T09:08:39Z)
• EditDuet: A Multi-Agent System for Video Non-Linear Editing [24.334561615501105]
  We propose to automate the core task of video editing, formulating it as sequential decision making process.<n>The Editor takes as input a collection of video clips together with natural language instructions and uses tools commonly found in video editing software to produce an edited sequence.<n>We evaluate our system's output video sequences qualitatively and quantitatively through a user study and find that our system vastly outperforms existing approaches in terms of coverage, time constraint satisfaction, and human preference.
  arXiv  Detail & Related papers  (2025-09-13T00:27:02Z)
• Image Editing As Programs with Diffusion Models [69.05164729625052]
  We introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture.<n>IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions into sequences of atomic operations.<n>Our framework delivers superior accuracy and semantic fidelity, particularly for complex, multi-step instructions.
  arXiv  Detail & Related papers  (2025-06-04T16:57:24Z)
• InFusion: Inject and Attention Fusion for Multi Concept Zero-Shot Text-based Video Editing [27.661609140918916]
  InFusion is a framework for zero-shot text-based video editing. It supports editing of multiple concepts with pixel-level control over diverse concepts mentioned in the editing prompt. Our framework is a low-cost alternative to one-shot tuned models for editing since it does not require training.
  arXiv  Detail & Related papers  (2023-07-22T17:05:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.