arXiv.org

[2511.02824] Kosmos: An AI Scientist for Autonomous Discovery

Kosmos: An AI Scientist for Autonomous Discovery

andrewwhite01

TechCrunch

Experts don’t think AI is ready to be a ‘co-scientist’

FutureHouse

About

Metaculus

Next Millenium Prize Problem Solved by AI

Announcing Edison Scientific

Endpoints News

Exclusive: Research institute FutureHouse debuts AI scientist and for-profit spinoff

SGRodriques

Elon Musk

Rishi Sunak

Kamala Harris

Bill Gates

Andrew Ng

Yoshua Bengio

Fei-Fei Li

Demis Hassabis

Melanie Mitchell

Sam Altman

Dario Amodei

Geoffrey Hinton

Yann LeCun

Gary Marcus

Max Tegmark

Connor Leahy

Eliezer Yudkowsky

Jaan Tallinn

Marc Andreessen

Eric Schmidt

Norbert Wiener

Arthur Clarke

Irving John Good

Claude Shannon

Hans Moravec

John Smart

There's a "wall of fear-mongering and doomerism" in the AI world right now.

"Worrying about AI today is like worrying about overpopulation on Mars."

Concerns that AI could pose a threat to humanity is "preposterously ridiculous."

Claiming AI poses an existential threat is "such an extreme" and risks "wip[ing] out some of its potential benefits."

"I'm more concerned about... the risks that are here and now [than the existential threat of AI]."

Current AI is "not anywhere close" to posing an existential threat but it could in the future.

AI is the "biggest existential threat" to humanity.

AGI's worst-case scenario would be "lights-out for all of us."

Powerful AI systems "taking control" pose an "existential threat."

AI has a "10 to 25 per cent" chance of destroying humanity.

"The most likely result of building a superhumanly smart AI... is that literally everyone on Earth will die."

Does AI Pose an Existential Threat to Humanity?

Stuart Russell

Shane Legg

Society is more likely to get "cat-level" or "dog-level" AI years before human-level AI.

"[W]e will eventually reach AGI... and quite possibly before the end of this century."

"Superhuman AIs" will be achieved "between a few years and a couple of decades."

"Digital intelligence" could overtake us within "5 to 20 years."

We may achieve "something like AGI or AGI-like in the next decade."

"[W]e could get to real AGI in the next decade."

"Human-level" AI could occur in "two or three years."

"I'd be surprised if we don't have AGI by [2029]."

Will AI Surpass Human Intelligence, and When?

Researchers developed Kosmos, an AI scientist system that automates data-driven discovery by performing iterative cycles of parallel data analysis, literature search and hypothesis generation over extended periods of up to 12 hours per run.</span

Researchers developed Kosmos, an AI scientist system that automates data-driven discovery by performing iterative cycles of parallel data analysis, literature search and hypothesis generation over extended periods of up to 12 hours per run.

The system uses a structured world model to coordinate information sharing between specialized agents, enabling coherent pursuit of research objectives across an average of 200 agent rollouts that collectively execute 42,000 lines of code.</span

The system uses a structured world model to coordinate information sharing between specialized agents, enabling coherent pursuit of research objectives across an average of 200 agent rollouts that collectively execute 42,000 lines of code.

Independent scientist evaluators found 79.4% of statements in Kosmos reports to be accurate, with higher accuracy rates for data analysis statements at 85.5% compared to interpretation statements which achieved 57.9% accuracy.</span

Independent scientist evaluators found 79.4% of statements in Kosmos reports to be accurate, with higher accuracy rates for data analysis statements at 85.5% compared to interpretation statements which achieved 57.9% accuracy.

Academic collaborators estimated that a single 20-cycle Kosmos run performed work equivalent to approximately 6 months of human research time, with the number of valuable scientific findings scaling linearly with the number of cycles.</span

Academic collaborators estimated that a single 20-cycle Kosmos run performed work equivalent to approximately 6 months of human research time, with the number of valuable scientific findings scaling linearly with the number of cycles.

The researchers report seven validated discoveries made by Kosmos spanning multiple scientific fields including metabolomics, materials science, neuroscience and statistical genetics, with three reproducing unpublished findings.</span

The researchers report seven validated discoveries made by Kosmos spanning multiple scientific fields including metabolomics, materials science, neuroscience and statistical genetics, with three reproducing unpublished findings.

Each statement in Kosmos scientific reports includes direct citations to either data analysis code or primary literature sources, ensuring complete traceability of the system's reasoning and enabling independent verification of findings.</span

Each statement in Kosmos scientific reports includes direct citations to either data analysis code or primary literature sources, ensuring complete traceability of the system's reasoning and enabling independent verification of findings.

AI Scientist 'Kosmos' Automates Research, Makes 7 Discoveries

AI Scientist 'Kosmos' Automates Research, Makes 7 Discoveries

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

LeCun

Marcus

Bengio

Hinton

Hassabis

Altman

Amodei

Musk

Go Deeper

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters

AI Scientist 'Kosmos' Automates Research, Makes 7 Discoveries

AI Scientist 'Kosmos' Automates Research, Makes 7 Discoveries

The Controversies

Andreessen

Ng

LeCun

Mitchell

Li

Bengio

Musk

Altman

Hinton

Amodei

Yudkowsky

LeCun

Marcus

Bengio

Hinton

Hassabis

Altman

Amodei

Musk

Go Deeper

Sign Up for Our Free NewslettersSign Up for Our Free Newsletters

Sign Up for Our Free Newsletters
Sign Up for Our Free Newsletters