Categories › AI & Agents › Thinking, planning & prompt tools
Solve competition math (IMO, Putnam, USAMO) with adversarial verification that catches what self-verification misses. Fresh-context verifiers attack proofs with specific failure patterns. Calibrated abstention over bluffing.
Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.