StoryEngine: A State-Grounded Agentic Framework for Video Storytelling

Hugging Face Daily Papers Papers
video-storytelling state-grounded agentic-framework long-form-video narrative-coherence visual-consistency benchmark

Summary

StoryEngine proposes a state-grounded agentic framework for video storytelling that maintains structured state representations to ensure narrative coherence and visual consistency. It demonstrates superior performance over state-of-the-art methods in comprehensive evaluations.

Despite recent progress in agentic multi-shot video generation, producing coherent and consistent long-form stories remains challenging. Existing agentic pipelines typically rely on textual shot plans or previously generated pixels, yet lack an explicit mechanism for propagating the consequences of story events and maintaining the video world state across shots. As a result, missing visual details may be reconstructed inaccurately, while visual drift may propagate across subsequent shots, undermining both narrative coherence and visual consistency. To address these challenges, we propose StoryEngine, a state-grounded agentic framework for video storytelling. StoryEngine establishes a separation between authoritative semantic plans and unreliable visual observations. Specifically, StoryEngine maintains a structured representation of entity placement and story-relevant states, and propagates event-induced changes to define the intended start and end states of each shot. To visually realize these states, StoryEngine constructs canonical references for recurring entities and environments, and compiles state and visual constraints into executable render plans. Meanwhile, to realize these states correctly, a bounded evaluation-guided repair loop further corrects local state inconsistencies. Together, these mechanisms preserve causal story progression and prevent local visual errors from propagating across shots. To comprehensively evaluate long-form storytelling, we construct a benchmark across diverse scenarios and visual styles, with metrics assessing storytelling quality, narrative coherence, and visual consistency. Experimental results demonstrate that StoryEngine consistently outperforms state-of-the-art methods across all evaluation dimensions, validating its effectiveness for coherent and consistent video storytelling.
Original Article
View Cached Full Text

Cached at: 09/30/26, 08:18 AM

Paper page - StoryEngine: A State-Grounded Agentic Framework for Video Storytelling

Source: https://huggingface.co/papers/2609.33627

Abstract

Despiterecentprogressinagenticmulti-shotvideogeneration,producingcoherentandconsistentlong-formstoriesremainschallenging.Existingagenticpipelinestypicallyrelyontextualshotplansorpreviouslygeneratedpixels,yetlackanexplicitmechanismforpropagatingtheconsequencesofstoryeventsandmaintainingthevideoworldstateacrossshots.Asaresult,missingvisualdetailsmaybereconstructedinaccurately,whilevisualdriftmaypropagateacrosssubsequentshots,underminingbothnarrativecoherenceandvisualconsistency.Toaddressthesechallenges,weproposeStoryEngine,astate-groundedagenticframeworkforvideostorytelling.StoryEngineestablishesaseparationbetweenauthoritativesemanticplansandunreliablevisualobservations.Specifically,StoryEnginemaintainsastructuredrepresentationofentityplacementandstory-relevantstates,andpropagatesevent-inducedchangestodefinetheintendedstartandendstatesofeachshot.Tovisuallyrealizethesestates,StoryEngineconstructscanonicalreferencesforrecurringentitiesandenvironments,andcompilesstateandvisualconstraintsintoexecutablerenderplans.Meanwhile,torealizethesestatescorrectly,aboundedevaluation-guidedrepairloopfurthercorrectslocalstateinconsistencies.Together,thesemechanismspreservecausalstoryprogressionandpreventlocalvisualerrorsfrompropagatingacrossshots.Tocomprehensivelyevaluatelong-formstorytelling,weconstructabenchmarkacrossdiversescenariosandvisualstyles,withmetricsassessingstorytellingquality,narrativecoherence,andvisualconsistency.ExperimentalresultsdemonstratethatStoryEngineconsistentlyoutperformsstate-of-the-artmethodsacrossallevaluationdimensions,validatingitseffectivenessforcoherentandconsistentvideostorytelling.

View arXiv pageView PDFProject pageGitHub6Add to collection

Get this paper in your agent:

hf papers read 2609\.33627

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.33627 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.33627 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.33627 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

From Pixels to States: Rethinking Interactive World Models as Game Engines

Hugging Face Daily Papers

This paper rethinks interactive world models as game engines by examining four key dimensions—action control, state dynamics, state-observation persistence, and real-time generation—and introduces a scalable data engine for Black Myth: Wukong with over 90 hours of gameplay data to advance state-aware game world modeling.

Any Time, Any Space: A World-State-Centric Framework for Agentic Video Generation

Hugging Face Daily Papers

提出 Any Time, Any Space (ATAS) 框架，将剧本编译为带显式位置、相机和事件时间引用的镜头请求，通过场景记忆和事件记忆实现长时程 agentic 视频生成的跨镜头时空一致性，在四种视频生成器上均提升一致性指标并取得最佳综合评分。