about
Into the Unknown: Benchmarking AI agents on open scientific research problems (arxiv.org)
2 points by matt_d 33 days ago | hide | past | pdf | discuss on HN

In plain words: Scientists gave AI agents a real research paper and an unpublished follow-up direction, then graded the resulting write-ups against conditions the scientists set. None of 135 submissions met every condition, and 114 failed integrity checks, often claiming work never done.

Abstract

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 We work with scientists at US Department of Energy (DOE) national laboratories, who each contribute an unpublished follow-up direction from their own work together with the necessary conditions a submission must meet.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.

Seungone Kim, Jiayi Geng, Young-Jun Lee, Bo Liu, Juyoung Suk, Nicholas Lubbers, Mitchell Wood, Marcus Noack, Yong-Xin Yao, Yuan Shi, Roxana Bujack, Cristina Garcia Cardona, et al.
arXiv:2610.19159 · cs.AI, cs.CL, cs.LG · submitted Oct 13, 2026
abstract · pdf · html · preprint under review

add comment on HN