Ben Fei

Despite LLMs excelling at identifying reviewer concerns, they falter in verifying if revisions truly resolve those issues, with the best achieving only a 0.501 score in evidence-based checks.

SciReasoner achieves a remarkable 31% improvement in Cellular Component annotation for low-homology proteins, showcasing the power of structural reasoning in AI.

Existing agents excel at structured tasks but falter in feedback-driven operations and long-horizon workflows, revealing critical gaps in their capabilities for scientific instrument control.

Automating scientific instruments is now as easy as mimicking a human using the GUI, unlocking faster and more reproducible research.