Skip to content
conftrace_

difficulty aware advantage reweighting

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

reward sparsity (1) concise reasoning (1) length-regularized reward (1) group relative policy optimization (1) mathematical reasoning (1) reinforcement learning (1)

Papers

GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models EMNLP 2025