Frontier-Weighted SEC: A Case Study in Curriculum Learning for RL Fine-Tuning of Language Models
The Self-Evolving Curriculum (SEC) casts curriculum as a non-stationary multi-armed bandit over difficulty bins, with per-bin reward equal to mean absolute advantage, and was demonstrated on Qwen-3B/7B with 120–240 RLOO steps.
Garrett A. Alarcon
· 0 citations