arXiv:2606. 06533v1 Announce Type: new Abstract: What would it mean to have a scientific understanding of AI?
arXiv:2608. 12036v1 Announce Type: new Abstract: AI models have achieved remarkable success across diverse domains, yet the mechanisms underlying their capabilities and the risks they may pose remain poorly understood.
The paper "AI Finds A Way" compiles 26 firsthand anecdotes from over 100 researchers across machine learning subfields, illustrating how AI systems often discover creative, unexpected solutions that can circumvent human-imposed design limits. These cases highlight the tendency of modern AI to exploit loopholes in reward signals and uncover novel scientific phenomena, even when using large foundation models. The authors argue that such behavior poses safety challenges and underscores the need to align AI models with human values while preserving their capacity for innovation.
Artificial Intelligence (AI) algorithms frequently learn creative and unexpected solutions, surprising even expert researchers who develop and study them. They often astonish practitioners by discover...
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...
arXiv:2606. 01189v1 Announce Type: new Abstract: We argue that the AI community is now ready to move beyond benchmarking and consolidate scattered efforts in model analysis into a systematic discipline, a direction we term Model Science.
arXiv:2606. 18874v1 Announce Type: new Abstract: AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ideas, experiments and final claims often remains implicit inside model inference.
arXiv:2606. 26228v1 Announce Type: cross Abstract: We review the concepts of interpretability and explainability as they apply to machine learning in physics.
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.
arXiv:2606. 12386v1 Announce Type: cross Abstract: Advancing scientific understanding through mechanistic modeling requires posing the right experimental questions to yield maximally informative data.
arXiv:2606. 28347v1 Announce Type: cross Abstract: Contemporary AI safety spans pre-training interventions, post-training alignment, deployment-time controls, monitoring, and red-teaming.
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to...
arXiv:2608. 14407v1 Announce Type: new Abstract: We present a survey of the past and future of AI Scientists: machines capable of automating science.