Lilong Wang

Verified data synthesis can dramatically elevate the skill-use performance of language models, producing thousands of executable trajectories that enhance agent capabilities.

OrthoPilot outperformed seasoned orthopaedic experts in diagnostic reasoning, achieving a 10.6% increase in management success for complex musculoskeletal cases.

ProtoPilot achieves a staggering 90.2% expert-preference rate in autonomous wet-lab experimentation, setting a new benchmark for protocol generation and execution.

LLMs can now dynamically create and refine their own scientific tools at test time, outperforming agents stuck with static toolsets.