AI News HubLIVE
原文2 min read

When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery

This paper introduces CARTOGRAPH, a verification layer for AI scientists that couples unresolved-subspace experiment steering, explicit ambiguity closure, and residual-based library inadequacy detection. It outperforms raw projection in five testbeds and demonstrates the ability to tentatively identify and then revoke out-of-library mechanisms. In a retrospective audit, it flagged all inconclusive claims from the A-Lab autonomous materials system while passing most confirmed claims.

SourcearXiv Machine LearningAuthor: Neel Tushar Shah, Manglam Kartik

[2606.07576] When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery

[Submitted on 26 May 2026]

Title:When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery

View a PDF of the paper titled When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery, by Neel Tushar Shah and Manglam Kartik

View PDF HTML (experimental)

Abstract:We present CARTOGRAPH, a verification layer for AI scientists that couples unresolved-subspace experiment steering (select), explicit ambiguity closure (resolve), and residual-based library inadequacy detection (refuse). Under a local linear-Gaussian bridge, raw unresolved projection is the isotropic unresolved Fisher-information trace, while CARTOGRAPH-A is the exact unresolved A-optimal rule; closed-form EIG and Box-Hill arise as local comparators rather than global equivalents. Across five testbeds, CARTOGRAPH-A beats raw projection 129W/0T/15L at d = 8 (p

new | recent | 2026-06

Change to browse by:

cs cs.ET cs.MA

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?)

IArxiv recommender toggle

IArxiv Recommender (What is IArxiv?)

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?)