A long-running autonomous AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → produced a machine-verified proof that checks against only Lean's standard axioms. It shows that formal verification can bound the trust problem for large AI-generated artifacts.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
