# EvoState: Closed-Loop Visual State Management for Long-Form Video Generation

arXiv: https://arxiv.org/abs/2606.16184 · HTML: https://mlsanity.com/paper/2606.16184/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 34 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 27 of 27)

- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [In-Context LoRA for Diffusion Transformers](https://mlsanity.com/paper/2410.23775/) (2024)
- [VideoDirectorGPT: Consistent Multi-scene Video Generation via LLM-Guided Planning](https://mlsanity.com/paper/2309.15091/) (2023)
- [StoryGAN: A Sequential Conditional GAN for Story Visualization](https://mlsanity.com/paper/1812.02784/) (2018)
- [Long Context Tuning for Video Generation](https://mlsanity.com/paper/2503.10589/) (2025)
- [Mixture of Contexts for Long Video Generation](https://mlsanity.com/paper/2508.21058/) (2025)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [Make-A-Story: Visual Memory Conditioned Consistent Story Generation](https://mlsanity.com/paper/2211.13319/) (2022)
- [Vlogger: Make Your Dream A Vlog](https://mlsanity.com/paper/2401.09414/) (2024)
- [HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives](https://mlsanity.com/paper/2510.20822/) (2025)
- [Captain Cinema: Towards Short Movie Generation](https://mlsanity.com/paper/2507.18634/) (2025)
- [DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion](https://mlsanity.com/paper/2407.12899/) (2024)
- [StoryMem: Multi-shot Long Video Storytelling with Memory](https://mlsanity.com/paper/2512.19539/) (2025)
- [ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models](https://mlsanity.com/paper/2505.07652/) (2025)
- [MultiShotMaster: A Controllable Multi-Shot Video Generation Framework](https://mlsanity.com/paper/2512.03041/) (2025)
- [EchoShot: Multi-Shot Portrait Video Generation](https://mlsanity.com/paper/2506.15838/) (2025)
- [FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation](https://mlsanity.com/paper/2506.18899/) (2025)
- [STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative](https://mlsanity.com/paper/2512.12372/) (2025)
- [CharaConsist: Fine-Grained Consistent Character Generation](https://mlsanity.com/paper/2507.11533/) (2025)
- [MoGA: Mixture-of-Groups Attention for End-to-End Long Video Generation](https://mlsanity.com/paper/2510.18692/) (2025)
- [STORYANCHORS: Generating Consistent Multi-Scene Story Frames for Long-Form Narratives](https://mlsanity.com/paper/2505.08350/) (2025)
- [MUSE: A Multi-agent Framework for Unconstrained Story Envisioning via Closed-Loop Cognitive Orchestration](https://mlsanity.com/paper/2602.03028/) (2026)

## Built on by (most cited first, 2 of 2)

- [Agentic Visual Generation: From Generative Models to Agentic Control](https://mlsanity.com/paper/2609.06758/) (2026)
- [Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation](https://mlsanity.com/paper/2609.37407/) (2026)

## Abstract (arXiv)

Multi-shot long-form video generation remains challenging due to identity drift and compounding inconsistencies across shots. Existing methods encode past shots as compressed context, implicit features, or retrieved frames, making it hard to tell whether new visual evidence is another view of an existing appearance, an evolved state of the same identity, or a newly introduced entity. We propose EvoState, an agentic framework that formulates multi-shot generation as entity-centric evolving visual state management, following a state-observation-update-propagation cycle. An entity-centric Visual State Memory separates persistent identity anchors from their evolved states and observations, so each shot retrieves the required state, accumulates complementary views, and reactivates earlier appearances without conflating them. A Visual State Analyzer reconciles the text-visual-memory triplet by observing generated visual evidence, updating generation conditions according to realized outcomes and memory states, and propagating inferred state transitions into memory and future prompts. As a result, generation is conditioned on an evolving state history grounded in what has been realized, rather than solely on planned textual descriptions. Experiments on our curated StoryBench benchmark demonstrate substantial improvements in identity preservation, state-transition correctness, and narrative coherence over state-of-the-art methods.