Toward autonomous science with agentic artificial intelligence.

Agentic AI systems like Co-Scientist, Robin, and Biomni can autonomously generate hypotheses, design experiments, analyze data, and refine reasoning, advancing scientific discovery.

• Why it matters: Understanding and developing autonomous scientific reasoning is crucial for accelerating biomedical research and addressing challenges such as hallucination, bias, and irreproducibility that threaten AI's reliability and safety.
• What they did: The authors review recent AI systems that demonstrate agentic capabilities in biomedicine, discuss scaling laws and autonomous labs, and explore the potential and challenges of integrating AI into scientific workflows.
• The result: This work highlights that responsible human-AI collaboration is essential for harnessing AI's transformative potential in science, enabling more efficient and reliable biomedical discoveries.