arXiv AI By Yu Yao, Jiayi Dong, Yang Yang, Shuiwang Ji, Ju Li

VerifiedLab: Harnessing Knowns for Unknowns

Read the original on arXiv AI →

VerifiedLab is a multi‑agent framework that transforms research records into active systems for laboratory experiments. It employs a team of AI scientists—principal investigator, librarian, specialists, gate, and critic—to reason over records field by field, verify claims against measured reliability, and decide whether to release or withhold information. Experiments on perovskite solar cells show that VerifiedLab can recover known physical trends, anticipate future device reports, and provide a trust metric for inherited literature.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Oct 31

PAPERBENCHX: Can AI Reproduce Science Across Disciplines?

PAPERBENCHX is a new benchmark that tests whether AI can reproduce scientific experiments across 12 disciplines, including electromagnetics, photonics, chemistry, materials science, biology, and robotics. It consists of 93 expert-constructed tasks, each providing a source paper, a public specification, and a domain-native scientific environment. The benchmark evaluates AI agents by having them reconstruct, execute, and diagnose key experiments, then replay submissions from scratch to score regenerated evidence against expert-validated criteria, revealing that current AI configurations fully reproduce only 14% of tasks.

By Ruoyu Wu, Zengji Tu, Aolong Sun, Tianyi Ma, Junren Li, Xinbo Xu, Li Fu, Ziyan Zhang, Pinrui Huang, Xiaochen Wang, Chengda Wu, Yutao Zhou, Jianjun Wu, Lin Chang, Baobao Chang, Liang Chen, Kuan Li
arXiv AI
Aug 14

Training AI Scientists to Replicate Research

arXiv:2608. 13331v1 Announce Type: cross Abstract: The replicability of papers is a cornerstone of scientific knowledge, ensuring the reliability of existing results and providing a base for further experiments.

By Damon Falck, Samer Sabri, Anja Surina, Thom Foster, Anya Sims, Sam Devlin, Dylan Rogers, Tantum Collins, Kaloyan Aleksiev, Louis Kirsch, Edward Hughes
Hugging Face Trending Papers
Jun 10

Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills

Scientific discovery workflows usually contain and rely heavily on lab notes, where researchers record observations, interpret uncertain results, and plan follow-up experiments. Such informative lab notes preserve evolving scientific reasoning and author uncertainty, rather than polished final results exhibited in publications, providing a valuable opportunity for AI to engage in scientific exploration at a more comprehensive and deeper level.