# MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration

arXiv: https://arxiv.org/abs/2602.03028 · HTML: https://mlsanity.com/paper/2602.03028/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 43 references that are in the map.
- First posted on arXiv 3 Feb 2026.

## Builds on (most cited first, 30 of 36)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [Imagen Video: High Definition Video Generation with Diffusion Models](https://mlsanity.com/paper/2210.02303/) (2022)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning](https://mlsanity.com/paper/2307.04725/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [AudioLDM: Text-to-Audio Generation with Latent Diffusion Models](https://mlsanity.com/paper/2301.12503/) (2023)
- [Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models](https://mlsanity.com/paper/2402.17177/) (2024)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [CosyVoice 2: Scalable Streaming Speech Synthesis with Large Language Models](https://mlsanity.com/paper/2412.10117/) (2024)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation](https://mlsanity.com/paper/2402.04324/) (2024)
- [PromptTTS: Controllable Text-to-Speech with Text Descriptions](https://mlsanity.com/paper/2211.12171/) (2022)
- [Large Multimodal Agents: A Survey](https://mlsanity.com/paper/2402.15116/) (2024)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis](https://mlsanity.com/paper/2207.09814/) (2022)
- [Vlogger: Make Your Dream A Vlog](https://mlsanity.com/paper/2401.09414/) (2024)
- [VideoWorld: Exploring Knowledge Learning from Unlabeled Videos](https://mlsanity.com/paper/2501.09781/) (2025)
- [Anim-Director: A Large Multimodal Model Powered Agent for Controllable Animation Video Generation](https://mlsanity.com/paper/2408.09787/) (2024)
- [VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention](https://mlsanity.com/paper/2503.15138/) (2025)
- [StoryAgent: Customized Storytelling Video Generation via Multi-Agent Collaboration](https://mlsanity.com/paper/2411.04925/) (2024)
- [MAViS: A Multi-Agent Framework for Long-Sequence Video Storytelling](https://mlsanity.com/paper/2508.08487/) (2025)
- [GRPose: Learning Graph Relations for Human Image Generation with Pose Priors](https://mlsanity.com/paper/2408.16540/) (2024)
- [MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation](https://mlsanity.com/paper/2501.01808/) (2025)
- [MotionStrata: Hierarchical Motion Latents for Compact Video Autoencoding](https://mlsanity.com/paper/2506.07136/) (2025)

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

- [GroundShot: Visually Consistent Multi-Shot Long Video Generation via Entity-Grounded Shot Scheduling](https://mlsanity.com/paper/2606.20799/) (2026)
- [EvoState: Closed-Loop Visual State Management for Long-Form Video Generation](https://mlsanity.com/paper/2606.16184/) (2026)
- [FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling](https://mlsanity.com/paper/2607.19038/) (2026)
- [Stable Curves, Unstable Items: Item-Level Scaling Heterogeneity in Video LLMs](https://mlsanity.com/paper/2608.07014/) (2026)
- [RiO-DETR: DETR for Real-time Oriented Object Detection](https://mlsanity.com/paper/2603.09411/) (2026)

## Abstract (arXiv)

Generating long-form audio-visual stories from a short user prompt remains challenging due to an intent-execution gap, where high-level narrative intent must be preserved across coherent, shot-level multimodal generation over long horizons. Existing approaches typically rely on feed-forward pipelines or prompt-only refinement, which often leads to semantic drift and identity inconsistency as sequences grow longer. We address this challenge by formulating storytelling as a closed-loop constraint enforcement problem and propose MUSE, a multi-agent framework that coordinates generation through an iterative plan-execute-verify-revise loop. MUSE translates narrative intent into explicit, machine-executable controls over identity, spatial composition, and temporal continuity, and applies targeted multimodal feedback to correct violations during generation. To evaluate open-ended storytelling without ground-truth references, we introduce MUSEBench, a reference-free evaluation protocol validated by human judgments. Experiments demonstrate that MUSE substantially improves long-horizon narrative coherence, cross-modal identity consistency, and cinematic quality compared with representative baselines.