DualOPSD: Closing the Feedback Loop in On-Policy Self-Distillation

arXiv:2608.26019 · cs.LG, cs.AI · Submitted 2026-08-26 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-08-26

Updated: 2026-10-13

Comments: preprint

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 27× in this paper · explained in 2 episodes
• Accuracy — 11× in this paper · explained in 1 episode
• Adaptation — 11× in this paper · explained in 1 episode
• Verifier — 11× in this paper · explained in 2 episodes
• GRPO — 8× in this paper · explained in 6 episodes
• Knowledge Distillation — 6× in this paper · explained in 11 episodes
• Self-distillation — 6× in this paper · explained in 6 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Thinking mode — 4× in this paper · explained in 2 episodes
• Benchmark — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• AdamW Optimizer — 2× in this paper · explained in 1 episode
• On-policy Self-Distillation (OPSD) — 2× in this paper · explained in 2 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Verifiable Rewards — 2× in this paper · explained in 2 episodes
• Adaptive Teaching — 1× in this paper · explained in 1 episode
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• LoRA Adapters — 1× in this paper · explained in 3 episodes
• On-Policy Distillation — 1× in this paper · explained in 3 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• MiniLLM: On-Policy Distillation of Large Language Models
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• Distilling the Knowledge in a Neural Network
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Qwen3 Technical Report
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

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