The Endless Exam: Mathematical Constructions from Today's Models toward Superintelligence
Endless Exam scores mathematical constructions without a cap; nine models fail to beat 30 published frontiers.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #verifiable-rewards
MInTRL: Off-policy Intervention can boost On-policy RL
MInTRL injects sparse judge corrections into on-policy RL rollouts, expanding exploration beyond on-policy sampling while preserving learnability on math and code benchmarks.