Answers are grounded in this paper and cite their sources.
Experimental evaluation demonstrates autonomous end-to-end scientific research in 288 human participants, highlighting the viability of closed-loop AI systems for empirical discovery.
Artificial intelligence systems are transforming scientific discovery by accelerating specific research tasks, from protein structure prediction to materials design, yet remain confined to narrow domains requiring substantial human oversight. Exponential growth of scientific literature and increasing domain specialization constrain researchers' capacity to synthesize knowledge across disciplines and develop unifying theories, motivating exploration of general-purpose AI systems for science. Here we show that a domain-agnostic, agentic AI Scientist system can independently navigate the scientific workflow -from hypothesis generation through data collection to manuscript preparation. The system autonomously designed and executed three psychological studies on visual working memory, mental rotation, and imagery vividness, executed online data collection with 288 participants, developed analysis pipelines through 8h+ continuous coding sessions, and produced completed manuscripts. The results demonstrate the capability of AI scientific discovery pipelines to conduct research with theoretical reasoning and methodological rigor comparable to experienced researchers, though with limitations in conceptual nuance and theoretical interpretation. This is a step toward embodied AI that can test hypotheses through real-world experiments, accelerating discovery by autonomously exploring regions of scientific space that human cognitive and resource constraints might otherwise leave unexplored. It raises important questions about the nature of scientific understanding and attribution of scientific credit.
No takes yet. Share an insight, caveat, or question.
Wehr et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: