跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 13 天前AI 評分46

盲目變異、選擇性保留:提升 AI 科學家的創意構想生成能力

Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists

AI 導讀

BVSR 框架透過在探索階段限制任務資訊,再利用同一任務已驗證提案及其結果,改善 AI 科學家的創意構想生成與候選篩選。在五個提案模型和 12 項科學任務的評估中,限制任務資訊提升了提案的原創性與非顯而易見程度;學習過往提案結果則可淘汰一半候選項目,同時保留大部分表現最佳的提案。

正文

Published on Nov 9

Authors:

,

,

,

,

Abstract

Scientific discovery requires ideas that are original, useful, and non-obvious. Yet AI scientists are typically given as much task information as possible during idea generation, which can anchor generation toward familiar approaches. Inspired by the cognitive framework of Blind Variation and Selective Retention (BVSR), we propose a discovery framework that separates these two roles of information: it generates proposals under deliberately limited task information to broaden exploration, then learns from proposals previously verified on the same task and their outcomes to retain promising candidates for costly empirical evaluation. We evaluate BVSR across five proposer models and 12 scientific tasks. Limiting task information substantially increases proposal originality and non-obviousness, and produces a larger share of highly creative and high-utility proposals than existing state-of-the-art prompting-based baselines. Learning from prior proposal outcomes on the task further improves candidate selection, discarding half of the candidates while retaining most top-performing proposals. When incorporated into existing AI-scientist workflows, BVSR achieves stronger discoveries across gene expression analysis, drug response prediction, anomaly detection, scaling law discovery, and brain activity prediction. These results suggest that effective AI scientists should use information differently across stages of discovery: constrain task-specific information during exploration while exploiting accumulated empirical experience on the task.

View arXiv page View PDF Project page GitHub 7 Add to collection

Get this paper in your agent:

hf papers read 2611.12184

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Xkev/SR-judger

Text Classification •

8B •

Updated 1 day ago

•

31

•

1

Datasets citing this paper 1

Xkev/BVSR-data

Preview •

Updated 1 day ago

•

73

•

1

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.12184 in a Space README.md to link it from this page.

Collections including this paper 1

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co