Skip to content
AI News HubLIVE
Original source2 min read

Verify2Act: Critic-Guided Latent World Models for Verifying Language-Conditioned Manipulation Plans

Summary

Verify2Act is a modular verification framework that separates semantic action proposal from latent physical verification. A VLM proposes candidate plans, a latent world model imagines each plan in DINOv2 feature space, and a dual-head critic checks the imagined rollouts for temporal consistency and goal satisfaction before execution. It achieves 83.3% task success across six language-conditioned tasks, significantly outperforming baselines.

SourcearXiv RoboticsAuthor: Chrisantus Eze, Christopher Crick
Verify2Act: Critic-Guided Latent World Models for Verifying Language-Conditioned Manipulation Plans
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 18 Nov 2026]

Title:Verify2Act: Critic-Guided Latent World Models for Verifying Language-Conditioned Manipulation Plans

View a PDF of the paper titled Verify2Act: Critic-Guided Latent World Models for Verifying Language-Conditioned Manipulation Plans, by Chrisantus Eze and Christopher Crick

View PDF HTML (experimental)

Abstract:Vision-Language Models (VLMs) can propose multi-step manipulation plans, but they have no grounded model of how a scene will change, and the pixel-level world models that could check those plans are slow and drift over long horizons. We present Verify2Act, a modular verification framework that separates semantic action proposal from latent physical verification. A VLM proposes candidate plans, a latent world model (V2A-WM) imagines each of them in the DINOv2 feature space, and a dual-head critic checks the imagined rollouts for temporal consistency and goal satisfaction before anything is executed. V2A-WM extends recent flow-matching world models with cross-attention action grounding and a causal temporal history window. We deploy the full system on a low-cost robot arm, training the world model and critic only on data generated in a digital twin. Across six language-conditioned tasks, Verify2Act reaches 83.3\% task success, compared with 61.7\% for a latent world model without our architectural changes, 53.3\% for the VLM alone, and 46.7\% for a pixel-diffusion world model. It verified every plan it executed and incurred no planning-induced failures: all of its failed episodes were caused by low-level grasp or placement slips. In simulation, Verify2Act obtains the highest five-task chain success on CALVIN among the compared baselines with 30$\times$ fewer reflective VLM calls than pixel-diffusion verification, and the highest success on cluttered nut assembly.

Subjects:

Robotics (cs.RO)

Cite as: arXiv:2611.25243 [cs.RO]

(or arXiv:2611.25243v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2611.25243

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Chrisantus Eze [view email] [v1] Wed, 18 Nov 2026 22:22:00 UTC (1,506 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Verify2Act: Critic-Guided Latent World Models for Verifying Language-Conditioned Manipulation Plans, by Chrisantus Eze and Christopher Crick

View PDF

HTML (experimental)

TeX Source

view license

Additional Features

Audio Summary

Current browse context:

cs.RO

new | recent | 2026-11

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

  • Verify2Act reaches 83.3% task success on six language-conditioned tasks, compared to 53.3% for the VLM alone and 46.7% for a pixel-diffusion world model.
  • The framework trains the world model and critic only on data generated in a digital twin and deploys on a low-cost robot arm.
  • On the CALVIN simulation benchmark, Verify2Act achieves the highest five-task chain success with 30× fewer reflective VLM calls than pixel-diffusion verification.

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