Transformation-Augmented GRPO for Enhancing Exploration in Reasoning of Large Language Models
cs.LG
Submitted: 2026-01-30
Updated: 2026-11-04
Code: https://github.com/huggingface/open-r1
Terminology
Sources
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Advances in GRPO for Generation Models: A Survey
- DAPO: An Open-Source LLM Reinforcement Learning System at Scale
- The Price of Format: Diversity Collapse in LLMs
- Rethinking Entropy Regularization in Large Reasoning Models
- The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs
- Measuring Mathematical Problem Solving With the MATH Dataset
- Self-Aligned Reward: Towards Effective and Efficient Reasoners
- Does Your Reasoning Model Implicitly Know When to Stop Thinking?
- Understanding R1-Zero-Like Training: A Critical Perspective
- SEED-GRPO: Semantic Entropy Enhanced GRPO for Uncertainty-Aware Policy Optimization
- ExGRPO: Learning to Reason from Experience
- Reinforcement Learning with Verifiable Rewards: GRPO's Effective Loss, Dynamics, and Success Amplification
- It Takes Two: Your GRPO Is Secretly DPO
- Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic
- Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends
- Proximal Policy Optimization Algorithms
- Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
- GPT-4 Technical Report
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis