Metraipolis › archive › dc_ed24932a0966
Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists — arXiv:2611.12184
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12184
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:48.105Z
- SHA-256 of the archived text
6700b2c3ba9758201aa2ed75dfdfe1e848cbe31983e1dfb24b74fd41d783b8c2- Stable URL of this page
https://metraipolis.com/documento/dc_ed24932a0966
How to cite
Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists — arXiv:2611.12184 — arXiv (en), https://arxiv.org/abs/2611.12184 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ed24932a0966 (Metraipolis archive dc_ed24932a0966, sha256 6700b2c3ba9758201aa2ed75dfdfe1e848cbe31983e1dfb24b74fd41d783b8c2)
BibTeX
@misc{dced24932a0966,
title = {Blind Variation, Selective Retention: Improving Creative Idea Generation in AI Scientists — arXiv:2611.12184},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12184},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ed24932a0966; sha256 6700b2c3ba9758201aa2ed75dfdfe1e848cbe31983e1dfb24b74fd41d783b8c2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12184. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2611.12184 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-11-10T18:37:52.451Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).