Metraipolis › archive › dc_cd373d5d226a
Into the Unknown: Benchmarking AI agents on open scientific research problems — arXiv:2610.19159
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19159
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T14:23:17.282Z
- SHA-256 of the archived text
00ab740e0a6b2afe3ada0a0c3b59fe6fe26900dae48cfabe745cd089b387552e- Stable URL of this page
https://metraipolis.com/documento/dc_cd373d5d226a
How to cite
Into the Unknown: Benchmarking AI agents on open scientific research problems — arXiv:2610.19159 — arXiv (en), https://arxiv.org/abs/2610.19159 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cd373d5d226a (Metraipolis archive dc_cd373d5d226a, sha256 00ab740e0a6b2afe3ada0a0c3b59fe6fe26900dae48cfabe745cd089b387552e)
BibTeX
@misc{dccd373d5d226a,
title = {Into the Unknown: Benchmarking AI agents on open scientific research problems — arXiv:2610.19159},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19159},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cd373d5d226a; sha256 00ab740e0a6b2afe3ada0a0c3b59fe6fe26900dae48cfabe745cd089b387552e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19159. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Can AI agents carry out research on open scientific problems? We introduce Into the Unknown, a benchmark that provides an agent with a science paper along with a research direction to pursue and tasks it to write a follow-up paper. We work with scientists at US Department of Energy (DOE) national laboratories, who each contribute an unpublished follow-up direction from their own work together with the necessary conditions a submission must meet. While assessing the quality of a follow-up paper is challenging in general, using these conditions to form a rubric makes evaluation more tractable for research problems that have no reference answer. We have nine frontier agents write 15 follow-ups each, spanning quantum computing, plasma physics, computational chemistry, materials science, and scientific machine learning domains. None of the 135 submissions satisfies all the conditions, and 114 fail our integrity check, most often because the paper claims work that was never done or reports numbers that contradict the recorded evidence. Overall, agents readily produce papers that look like follow-ups, but none meets the standard of the domain scientist, leaving substantial headroom. Our code and data are publicly available. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.19159 — 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 2026-10-15T13:53:35.836Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).