Learning from Think-Mode Advantage via On-Policy Distillation

arXiv:2609.37044 · cs.CL · Submitted 2026-09-29 · Read on arXiv

cs.CL

Submitted: 2026-09-29

Updated: 2026-09-30

Terminology

• Trace — 64× in this paper · explained in 2 episodes
• Distillation — 30× in this paper · explained in 2 episodes
• On-Policy Distillation — 7× in this paper · explained in 3 episodes
• Benchmark — 6× in this paper · explained in 2 episodes
• Self-distillation — 6× in this paper · explained in 6 episodes
• Aggregation — 5× in this paper · explained in 1 episode
• Ablation — 4× in this paper · explained in 1 episode
• Knowledge Distillation — 3× in this paper · explained in 11 episodes
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• International Conference on Learning Representations — 2× in this paper
• Meeting of the Association for Computational Linguistics — 2× in this paper
• Verifier — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Calibration — 1× in this paper · explained in 7 episodes
• Continual Learning — 1× in this paper · explained in 2 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Provenance — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• Skywork Open Reasoner 1 Technical Report
• Distilling the Knowledge in a Neural Network
• Reinforcement Learning via Self-Distillation
• Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance
• Entropy-Aware On-Policy Distillation of Language Models
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
• Self-Distillation Enables Continual Learning
• Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
• Qwen3 Technical Report
• On-Policy Context Distillation for Language Models
• Distilling System 2 into System 1
• DAPO: An Open-Source LLM Reinforcement Learning System at Scale
• On-Policy Distillation with Best-of-N Teacher Rollout Selection
• Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering