GRPO Training Dynamics for Small Language Models

arXiv:2609.39321 · cs.LG, cs.AI · Submitted 2026-09-30 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/project-numina/aimo-progress-prize

Terminology

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

Sources

• On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
• Mechanistic Interpretability for Large Language Model Alignment: Progress, Challenges, and Future Directions
• A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models
• Hyperparameter Optimisation with Practical Interpretability and Explanation Methods in Probabilistic Curriculum Learning
• Proximal Policy Optimization Algorithms
• Tina: Tiny Reasoning Models via LoRA
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks