advantage-reweighting

STARE addresses policy entropy collapse in GRPO-based reinforcement learning for large language models by introducing surprisal-guided token-level advantage reweighting and target-entropy regulation, achieving 4%-8% accuracy gains on AIME benchmarks.

GRAIL introduces gradient-reweighted advantages to improve token-level credit assignment in reinforcement learning for LLM reasoning, outperforming GRPO across multiple models.