Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO

arXiv:2609.36932 · cs.AI · Submitted 2026-09-29 · Read on arXiv

cs.AI

Submitted: 2026-09-29

Updated: 2026-10-03

Code: https://github.com/Nicozwy/FastRL

Terminology

• GRPO — 1× in this paper · explained in 6 episodes
• Pruning — 1× in this paper · explained in 4 episodes

Sources

• Measuring Mathematical Problem Solving With the MATH Dataset
• MC-GRPO: Median-Centered Group Relative Policy Optimization for Small-Rollout Reinforcement Learning
• LIMR: Less is More for RL Scaling
• MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
• PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Group Sequence Policy Optimization

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems