arXiv:2607. 12474v1 Announce Type: new Abstract: Recent advances in foundation models have transformed AI for Science, enabling remarkably accurate predictive performance across domains ranging from protein folding to weather forecasting.
By Ingmar Posner, Anson Lei, Bernhard Sch\"olkopf
arXiv:2606. 02632v1 Announce Type: cross Abstract: Modern Machine Learning (ML) and Artificial Intelligence (AI) models, especially large language models (LLMs), are increasingly used to generate scientific hypotheses and mechanistic explanations from observational data.
By Tyler H. McCormick
arXiv:2607. 18777v1 Announce Type: new Abstract: Evaluating machine learning in scientific domains requires separating correct predictions from correct reasons under realistic distribution shifts.
By Dongkwan Kim, Yiming Gao, Yining Yang, Yang Shen
arXiv:2606. 06533v1 Announce Type: new Abstract: What would it mean to have a scientific understanding of AI?
By Stella Biderman, Mohammad Aflah Khan, Niloofar Mireshghallah, Catherine Arnett, Fazl Barez, Naomi Saphra
arXiv:2608.30165v1 Announce Type: cross
Abstract: Scientific progress depends not only on finding solutions, but on learning the rules that explain why they work and using that understanding to desig...
By Arya S. Rao, Rodrigo I. Castro, Sager J. Gosai, Kenneth B. Hsu, Yasha Ektefaie, Shantanu Singh, Sangeeta N. Bhatia, Steven K. Reilly, Ryan Tewhey, Eric S. Lander, Pardis C. Sabeti
The paper introduces SAEScientist-Bench, a benchmark that tests whether AI agents can autonomously conduct mechanistic interpretability research using Sparse Autoencoders (SAEs). Agents are tasked with designing contrastive probes and navigating a large feature dictionary in Gemma-2-9B-IT to identify optimal features for a target concept, with performance measured against expert-curated references on activation rank, concept selectivity, and causal steering. Results show that while frontier agents can discover features and outperform controls, they still lag behind expert baselines, especially in causal steering, highlighting both the potential and current limitations of closed-loop autonomous AI research.
By Yuqiao Tan, Shizhu He, Jun Zhao, Kang Liu