Skip to content
AI News HubLIVE
Original source2 min read

MVAgent: Multi-Agent Video Generation via Consistent Condition Construction and Shot-Level Policy Optimization

Summary

arXiv:2609.30609v1 Announce Type: new Abstract: Multi-shot agentic video generation requires consistent character appearance, stable spatial layout across camera angles, and continuous character state between shots. When every shot is a separate request to a frozen generator, repeated text does not determine appearance, layout or state. We therefore recast the problem as condition construction and present MVAgent, a multi-agent pipeline whose agents collaborate through typed conditioning inputs. Because an environment image shows one viewpoint, a Spatial Grounding agent samples views from generated camera-traversal clips and anchors each shot to the view matching its framing. As generated shots drift from the plan, an Observer records how each shot ends in a continuity memory, from which…

SourcearXiv Computer VisionAuthor: Xiangyu Kong, Wenjie Zhou, Fengping Tian, Lihua Fang, Haoqin Sun, Chenyang Lyu, Longyue Wang, Weihua Luo
MVAgent: Multi-Agent Video Generation via Consistent Condition Construction and Shot-Level Policy Optimization
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 24 Sep 2026]

Title:MVAgent: Multi-Agent Video Generation via Consistent Condition Construction and Shot-Level Policy Optimization

View a PDF of the paper titled MVAgent: Multi-Agent Video Generation via Consistent Condition Construction and Shot-Level Policy Optimization, by Xiangyu Kong and 7 other authors

View PDF HTML (experimental)

Abstract:Multi-shot agentic video generation requires consistent character appearance, stable spatial layout across camera angles, and continuous character state between shots. When every shot is a separate request to a frozen generator, repeated text does not determine appearance, layout or state. We therefore recast the problem as condition construction and present MVAgent, a multi-agent pipeline whose agents collaborate through typed conditioning inputs. Because an environment image shows one viewpoint, a Spatial Grounding agent samples views from generated camera-traversal clips and anchors each shot to the view matching its framing. As generated shots drift from the plan, an Observer records how each shot ends in a continuity memory, from which a Transition agent builds character action and spatial references for the next shot. An Orchestrator composes these inputs into each request. Since a request reveals its effect only after rendering, we train it by agentic reinforcement learning with Trunk-GDPO, which compares rendered candidates at every shot rather than once per video and continues the best as the trunk. With generator and judges frozen, MVAgent attains the highest cross-shot consistency and narrative-planning quality among the compared methods on ViMax-Bench and is preferred over the strongest agentic baseline in human evaluation.

Comments: 5 pages, 2 figures

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2609.30609 [cs.CV]

(or arXiv:2609.30609v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2609.30609

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Xiangyu Kong [view email] [v1] Thu, 24 Sep 2026 22:47:40 UTC (5,935 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled MVAgent: Multi-Agent Video Generation via Consistent Condition Construction and Shot-Level Policy Optimization, by Xiangyu Kong and 7 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-09

Change to browse by:

cs

References & Citations

NASA ADS

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

  • AI generation is temporarily unavailable; this entry was preserved with deterministic fallback metadata.
  • arXiv:2609.30609v1 Announce Type: new Abstract: Multi-shot agentic video generation requires consistent character appearance, stable spatial layout across camera angles, and conti…

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