AI News HubLIVE
原文2 min read

VLADriveBench: Evaluating CoT-Action Relationship in VLA for Autonomous Driving

VLADriveBench is a new framework to evaluate whether chain-of-thought (CoT) reasoning in vision-language-action (VLA) models is relevant, consistent, and causally connected to driving trajectories. It combines observational metrics (mentioning, hallucination, contradiction, action alignment) with a CoT intervention protocol. Applied to three models across two architectures, it reveals that observational and causal analyses can diverge sharply: ORION scores high on observational alignment but its CoT is epiphenomenal, while Alpamayo v1.5 scores lower yet its CoT is strongly causal, with visual salience gating the extent of CoT influence.

SourcearXiv Computer VisionAuthor: Thach Nguyen, Danhua Guo, Tom Lampo, Fei Wu, Burhan Yaman

[2606.12706] VLADriveBench: Evaluating CoT-Action Relationship in VLA for Autonomous Driving

[Submitted on 10 Jun 2026]

Title:VLADriveBench: Evaluating CoT-Action Relationship in VLA for Autonomous Driving

View a PDF of the paper titled VLADriveBench: Evaluating CoT-Action Relationship in VLA for Autonomous Driving, by Thach Nguyen and 4 other authors

View PDF HTML (experimental)

Abstract:Vision-language-action (VLA) models generate chain-of-thought (CoT) reasoning alongside driving trajectories, but existing benchmarks evaluate only trajectory quality and do not assess whether the CoT is relevant, consistent, or causally connected to the driving action. We introduce VLADriveBench, a framework that combines observational metrics (mentioning, hallucination, contradiction, action alignment) with a CoT intervention protocol to provide complementary views of the CoT-action relationship. Applying VLADriveBench to three models across two architectures, we find that the two analyses can diverge sharply: ORION scores highest on observational alignment yet its CoT is epiphenomenal, while Alpamayo v1.5 scores lower yet its CoT is strongly causal, with visual salience gating the extent of CoT influence.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2606.12706 [cs.CV]

(or arXiv:2606.12706v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2606.12706

arXiv-issued DOI via DataCite

Submission history

From: Thach Nguyen [view email] [v1] Wed, 10 Jun 2026 21:53:33 UTC (58 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled VLADriveBench: Evaluating CoT-Action Relationship in VLA for Autonomous Driving, by Thach Nguyen and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-06

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?)