Metraipolis › archive › dc_faa2e12ffd1c

Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning — arXiv:2608.26809

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.26809
License (as archived)
CC0-1.0
Archived
2026-10-17T18:59:41.300Z
SHA-256 of the archived text
74b2ce3873b1c64fb5feab10dfc18fa28014b1bb4a75b3b5ec4f940733e5e895
Stable URL of this page
https://metraipolis.com/documento/dc_faa2e12ffd1c

How to cite

Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning — arXiv:2608.26809 — arXiv (en), https://arxiv.org/abs/2608.26809 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_faa2e12ffd1c (Metraipolis archive dc_faa2e12ffd1c, sha256 74b2ce3873b1c64fb5feab10dfc18fa28014b1bb4a75b3b5ec4f940733e5e895)
BibTeX
@misc{dcfaa2e12ffd1c,
  title = {Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning — arXiv:2608.26809},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.26809},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_faa2e12ffd1c; sha256 74b2ce3873b1c64fb5feab10dfc18fa28014b1bb4a75b3b5ec4f940733e5e895},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.26809. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-28 in cs.MM).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.26809 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-17T18:31:14.484Z dalla pagina https://arxiv.org/catchup/cs.MM/2026-08-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).