DiffGate: Difficulty-Gated Teacher Guidance for On-Policy Distillation

arXiv:2610.04596 · cs.LG · Submitted 2026-10-03 · Read on arXiv

cs.LG

Submitted: 2026-10-03

Updated: 2026-10-03

Code: https://github.com/volcengine/verl

Terminology

• Distillation — 1× in this paper · explained in 2 episodes
• On-Policy Distillation — 1× in this paper · explained in 3 episodes

Sources

• Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why
• H squared SD: Hybrid Hindsight Self-Distillation
• Evaluating Large Language Models Trained on Code
• Training Verifiers to Solve Math Word Problems
• Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
• Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
• When Teacher Guidance Misleads: Reward-Aligned On-Policy Distillation
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Measuring Massive Multitask Language Understanding
• Distilling the Knowledge in a Neural Network
• Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
• Rethinking Entropy Regularization in Large Reasoning Models
• Entropy-Aware On-Policy Distillation of Language Models
• CoDistill-GRPO: A Co-Distillation Recipe for Efficient Group Relative Policy Optimization
• TACO: Topics in Algorithmic COde generation dataset
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence
• Understanding R1-Zero-Like Training: A Critical Perspective
• On the Policy Gradient Foundations of Group Relative Policy Optimization: Credit Assignment, Gradient Sparsity, and Rank Collapse
• Reinforcement Learning with Verifiable Rewards: GRPO's Effective Loss, Dynamics, and Success Amplification

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