# Soap2Soap: Long Cinematic Video Remaking via Multi-Agent Collaboration

arXiv: https://arxiv.org/abs/2605.17423 · HTML: https://mlsanity.com/paper/2605.17423/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 52 references that are in the map.
- First posted on arXiv 17 May 2026.

## Builds on (most cited first, 30 of 43)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2212.11565/) (2022)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [ViperGPT: Visual Inference via Python Execution for Reasoning](https://mlsanity.com/paper/2303.08128/) (2023)
- [VACE: All-in-One Video Creation and Editing](https://mlsanity.com/paper/2503.07598/) (2025)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration](https://mlsanity.com/paper/2307.05300/) (2023)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [Video Understanding with Large Language Models: A Survey](https://mlsanity.com/paper/2312.17432/) (2023)
- [Learning Video Representations from Large Language Models](https://mlsanity.com/paper/2212.04501/) (2022)
- [VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset](https://mlsanity.com/paper/2305.18500/) (2023)
- [Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models](https://mlsanity.com/paper/2504.12626/) (2025)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [Theory of Mind for Multi-Agent Collaboration via Large Language Models](https://mlsanity.com/paper/2310.10701/) (2023)
- [AdaWorld: Learning Adaptable World Models with Latent Actions](https://mlsanity.com/paper/2503.18938/) (2025)
- [An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM](https://mlsanity.com/paper/2403.18406/) (2024)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [MM-VID: Advancing Video Understanding with GPT-4V(ision)](https://mlsanity.com/paper/2310.19773/) (2023)
- [MoReVQA: Exploring Modular Reasoning Models for Video Question Answering](https://mlsanity.com/paper/2404.06511/) (2024)
- [Kling-Omni Technical Report](https://mlsanity.com/paper/2512.16776/) (2025)
- [Long-Context State-Space Video World Models](https://mlsanity.com/paper/2505.20171/) (2025)
- [EventHallusion: Diagnosing Event Hallucinations in Video LLMs](https://mlsanity.com/paper/2409.16597/) (2024)
- [Language Repository for Long Video Understanding](https://mlsanity.com/paper/2403.14622/) (2024)
- [DMD: A Large-Scale Multi-Modal Driver Monitoring Dataset for Attention and Alertness Analysis](https://mlsanity.com/paper/2008.12085/) (2020)
- [Video ChatCaptioner: Towards Enriched Spatiotemporal Descriptions](https://mlsanity.com/paper/2304.04227/) (2023)
- [StoryMem: Multi-shot Long Video Storytelling with Memory](https://mlsanity.com/paper/2512.19539/) (2025)
- [ProcessPainter: Learn Painting Process from Sequence Data](https://mlsanity.com/paper/2406.06062/) (2024)
- [MultiShotMaster: A Controllable Multi-Shot Video Generation Framework](https://mlsanity.com/paper/2512.03041/) (2025)

## Built on by (most cited first, 5 of 5)

- [AVA-Encoder: Towards Agent-Native Video Representation Learning](https://mlsanity.com/paper/2608.12313/) (2026)
- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [Prompt-Adapter Context Routing for Parameter-Efficient Multi-Shot Long Video Extrapolation](https://mlsanity.com/paper/2607.06481/) (2026)
- [Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning](https://mlsanity.com/paper/2608.26809/) (2026)
- [DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation](https://mlsanity.com/paper/2609.00646/) (2026)

## Abstract (arXiv)

We study series-level cinematic remaking, a long-horizon video-to-video generation problem that localizes full episodes or films via stylization or actor replacement while strictly preserving narrative structure, motion choreography, and character identity across hundreds of shots. Existing video generation and editing pipelines often break down in this regime due to compounding identity drift, background mutation, and semantic erosion under large camera motions and viewpoint changes. We propose Soap2Soap, a multi-agent framework that enforces long-term language-visual consistency through a Dual-Bridge Consistency mechanism: a scene-aware JSON screenplay serving as a persistent semantic backbone, and dynamically allocated visual reference anchors at both scene and shot levels. To suppress drift before video synthesis, we introduce batch keyframe consistency, jointly generating multiple keyframes in a shared latent context via a grid-based formulation. A closed-loop verification agent further audits identity, stability, and alignment to trigger selective regeneration. Experiments on SoapBench demonstrate strong improvements over commercial video generation APIs in long-term consistency and narrative fidelity.