← Back to all news
arXiv AI By Taiming Lu, Sachin Konan, Zhuang Liu

Scientist World: Grow a Research World for AI-Scientists

Read the original on arXiv AI →

The paper introduces Scientist World, a platform that transforms research papers into executable environments for AI-Scientists. By extracting open-ended research questions and reproducing proposed methods, the system evaluates AI-Scientists against human authors and has released 1,000 verified environments. The study reports that frontier AI-Scientists surpass human researchers 74% of the time and that training on this platform can significantly boost model performance in research ideation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 18

ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI

The paper introduces ScientistTwo, a fully autonomous multi‑agent framework that takes a scientific problem, establishes baselines, generates hypotheses, and coordinates specialized agents to conduct an end‑to‑end discovery cycle without human intervention. It rigorously tests and refines its methods through automated experiments, ablation studies, and a closed‑loop peer‑review engine. Benchmarking against top conferences (ICLR, ICML, NeurIPS) shows that ScientistTwo produces expert‑level, publishable papers and codebases that outperform human state‑of‑the‑art models and receive higher review ratings under automated AI review.

By Jaehyun Nam, Jinsung Yoon, Yanzhou Pan, Yubo Wang, Rui Meng, Parthasarathy Ranganathan, Tomas Pfister
agentsbenchmarks
More like this →
arXiv AI
Sep 25

AI in Science: Early Insights

The paper "AI in Science: Early Insights" analyzes AI’s impact on scientific work using data from 15 million Gemini interactions, 2,600 specialized AI models, and a survey of 600 scientists. It finds widespread AI adoption, complementary use of large language models and specialized tools, significant productivity gains of about seven hours per week, and a shift in research bottlenecks toward hypothesis backlog and verification needs. The study suggests AI can boost scientific productivity but its full effect depends on addressing new downstream challenges.

By Mihai Codreanu, Alex Imas, Juan Mateos-Garcia, Joseph Emmens, Evalyne Muiruri, Arthur Turrell, Julian Jacobs, Atoosa Kasirzadeh, Ana Trisovic, Yiyuan Chen, Tanya Rodchenko, Catherine Pollard, Scott Strand, Daniel Rock, Zanna Iscenko, Fabien Curto Millet, Neil Thompson, James Manyika
llms
More like this →
arXiv AI
Jun 8

Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle

arXiv:2606. 07462v1 Announce Type: new Abstract: As foundation models advance and agent scaffolding becomes increasingly sophisticated, agents have demonstrated remarkable proficiency in complex, long-horizon coding tasks and even autonomous experiment execution.

By Jiayu Wang, Weijiang Lv, Bowen Fu, Jing Fu, Jiayi Song, Lingyu Zhang, Lanxuan Xue, Luodi Chen, Zepeng Xin, Kaiyu Li, Xiangyong Cao
llmsagentsbenchmarks
More like this →