Paper Detail

Scientist World: Grow a Research World for AI-Scientists

Taiming Lu, Sachin Konan, Zhuang Liu

arxiv Score 6.2

Published 2026-11-05 · First seen 2026-11-07

General AI

Abstract

AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted $-$ centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but not runnable, so we build Scientist World for them: every research paper becomes an executable environment. Our autonomous pipeline extracts each paper's open-ended research question and reproduces its proposed method as the baseline; an AI-Scientist entering the environment is evaluated against what the human authors achieved. We release the first 1,000 verified environments. With the world as an evaluation, we found that frontier AI-Scientists can already surpass the human researchers 74% of the time. As a record of how AI does science, it contains 6,400 hours of research traces, with every idea, experiment, failure, and success. As a training ground, we are able to raise (+158%) a small model to match frontier models in research ideation. At last, AI-Scientists' own world has arrived, grown from and growing with science itself.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{lu2026scientist,
  title = {Scientist World: Grow a Research World for AI-Scientists},
  author = {Taiming Lu and Sachin Konan and Zhuang Liu},
  year = {2026},
  abstract = {AI-Scientists arrived, but a world for them to grow in did not. Human scientists take theirs for granted \$-\$ centuries of open problems and shared ideas, waiting in the scientific literature. To AI-Scientists, that world is readable but not runnable, so we build Scientist World for them: every research paper becomes an executable environment. Our autonomous pipeline extracts each paper's open-ended research question and reproduces its proposed method as the baseline; an AI-Scientist entering the},
  url = {https://arxiv.org/abs/2611.08478},
  keywords = {cs.AI, cs.CL, cs.LG, Frontier, Pipeline (software), Executable, Computer science, Scientific discovery},
  eprint = {2611.08478},
  archiveprefix = {arXiv},
}

Metadata

{}