DSDR: Dual-Scale Diversity Regularization for Exploration in LLM Reasoning
Paper • 2602.19895 • Published • 14
XXPO/XXRL
-
-
SetPO: Set-Level Policy Optimization for Diversity-Preserving LLM Reasoning
Paper • 2602.01062 • Published -
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
Paper • 2602.06717 • Published • 74 -
MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning
Paper • 2601.22582 • Published -
AMIR-GRPO: Inducing Implicit Preference Signals into GRPO
Paper • 2601.03661 • Published -
Clipping-Free Policy Optimization for Large Language Models
Paper • 2601.22801 • Published • 3 -
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training
Paper • 2602.10693 • Published • 220 -
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
Paper • 2602.15620 • Published • 3 -
Experiential Reinforcement Learning
Paper • 2602.13949 • Published • 72