AI Paper Atlas

Research map / Large language models / AI and society

DeepScientist: Advancing Frontier-Pushing Scientific Findings Progressively

Yixuan Weng, Minjun Zhu, Qiujie Xie, QiYao Sun, Zhen Lin, Sifan Liu, Yue Zhang

ICLR 2026 · Large language models › AI and society · approach: Social-science view of AI evaluation

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add surrogate-model plus UCB idea selection before implementation (ablation)DeepScientist · Idea success ratesuccess rate: about 0% -> approximately 1-3%Improved
scale parallel GPUs with shared Findings Memory (ablation)DeepScientist · Progress findings in one weeknumber of SOTA-surpassing findings: one (4 GPUs) -> eleven (16 GPUs)Improved
autonomous redesign by DeepScientist (A2P) over All-at-OnceAll at Once · Who&Whenaccuracy: +183.7%Improved
autonomous redesign by DeepScientist (ACRA) over TokenRecyclingTokenRecycling · MBPPtokens/second: 190.25 -> 193.90Improved
autonomous redesign by DeepScientist (T-Detect, TDT, PA-Detect) over FastDetectGPTFastDetectGPT · RAIDAUROC: +7.9%Improved
DeepScientist papers vs other AI Scientist systems under automated reviewDeepScientist · DeepReviewer-14Brating: 5.90 vs best baseline 4.63Improved
DeepScientist papers vs ICLR 2025 average under human reviewDeepScientist · Human program committeerating: 5.00 vs 5.08No clear effect
human review of individual generated papersPA-Detect and ACRA · Human program committeerating: 4.33 vs 5.67 for TDT and A2PHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy