FormalScience: Scalable Human-in-the-Loop Autoformalisation of Science with Agentic Code Generation in Lean
Formalising informal mathematical reasoning into formally verifiable code is a significant challenge for large language models. In scientific fields such as physics, domain-specific machinery (\textit{e.g.} Dirac notation, vector calculus) imposes additional formalisation challen...
ArXiv CS.AI
Source
Generated insight by OnAirToday AI
This research tackles the difficult problem of translating informal scientific reasoning, like that in physics, into verifiable code, opening doors for AI to more rigorously assist in scientific discovery. By introducing a human-in-the-loop system, it makes formal verification accessible to domain experts without requiring deep programming knowledge.
Get the day's AI news in one short email. Free.
Comments
Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.