Skip to content
AI News HubLIVE
Original source2 min read

DyCraft: An Agentic System for Long-Horizon 4D Scene Generation

Summary

DyCraft breaks long-horizon animation generation into planning, static scene construction, and 3D storyboard keyframes, enabling coding agents to build and debug local motion step by step and reducing physical violations such as interpenetration and lack of support.

SourcearXiv Computer VisionAuthor: Jeff Tan, Hang Dai, Zeqian Long, Yanzhe Lyu, R. Kenny Jones, Shangzhe Wu, Chen Geng, Jiajun Wu
DyCraft: An Agentic System for Long-Horizon 4D Scene Generation
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[Submitted on 29 Oct 2026]

Title:DyCraft: An Agentic System for Long-Horizon 4D Scene Generation

View a PDF of the paper titled DyCraft: An Agentic System for Long-Horizon 4D Scene Generation, by Jeff Tan and 7 other authors

View PDF HTML (experimental)

Abstract:While frontier coding agents can generate high-quality 3D scenes and articulated assets, they struggle to create coherent long-horizon animations. When equipped with general-purpose harnesses, they frequently produce physically implausible outputs, generating objects that interpenetrate, lack physical support, or move unnaturally. Such bare agents struggle to repair these errors because they default to scripting the full animation in one pass, making it difficult to verify their work and disentangle complex spatiotemporal constraints. Drawing on the practice of human animators, we introduce DyCraft, a system for animated 3D scene generation that breaks animation into steps that coding agents can more reliably solve. DyCraft first expands the user's prompt into a detailed plan and builds a static scene. It then creates a 3D storyboard of key animation poses, where each frame is a static 3D scene that the agent can build and debug in isolation. Storyboarding decomposes the problem into pairs of verified start and end states, allowing the agent to author local motion between them with a collection of motion authoring tools. We evaluate DyCraft on 24 long-horizon, multi-shot animation tasks covering humanoid robots, human and animal characters, and physical mechanisms. Compared with a native GPT-6 agent in Codex and prior agentic baselines, DyCraft substantially reduces physical violations and generates higher-quality animated 3D scenes that are more often preferred by human raters.

Comments: Project page: this https URL

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2610.40754 [cs.CV]

(or arXiv:2610.40754v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2610.40754

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Jeff Tan [view email] [v1] Thu, 29 Oct 2026 16:42:04 UTC (17,953 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled DyCraft: An Agentic System for Long-Horizon 4D Scene Generation, by Jeff Tan and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.CV

new | recent | 2026-10

Change to browse by:

cs

References & Citations

SciX

Google Scholar

Semantic Scholar

Loading...

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • DyCraft is inspired by human animator workflows and decomposes long-horizon animation into verifiable sub-steps.
  • The system first expands a prompt into a detailed plan and builds a static scene, then creates a 3D storyboard of key poses.
  • On 24 long-horizon multi-shot tasks, DyCraft substantially reduces physical violations compared with a native GPT-6 agent and prior baselines.
  • Human raters more often prefer the higher-quality animated 3D scenes generated by DyCraft.

Highlights and analysis are generated automatically and may contain errors. Check the original source.

More recent stories on this topic · Agents