Solving Without Stopping: On-Policy Distillation at Small Scale

arXiv:2609.37326 · cs.AI, cs.CL · Submitted 2026-09-29 · Read on arXiv

cs.AI, cs.CL

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Distillation — 98× in this paper · explained in 2 episodes
• Benchmark — 59× in this paper · explained in 2 episodes
• Thinking mode — 36× in this paper · explained in 2 episodes
• On-Policy Distillation — 26× in this paper · explained in 3 episodes
• Accuracy — 17× in this paper · explained in 1 episode
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• In International Conference on Learning Representations — 4× in this paper
• International Conference on Machine Learning — 3× in this paper
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Abstention — 2× in this paper · explained in 1 episode
• Generative AI — 2× in this paper · explained in 2 episodes
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Credit assignment — 1× in this paper · explained in 3 episodes
• Empirical Methods in Natural Language Processing — 1× in this paper
• Failure Modes — 1× in this paper · explained in 3 episodes
• Regret — 1× in this paper · explained in 3 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Test-time Scaling — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling
• Distilling the Knowledge in a Neural Network
• Rethinking On-Policy Self-Distillation for Thinking Models
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation
• Outcome-Confounded Local Supervision in On-Policy Distillation
• Demystifying On-Policy Distillation: Roles, Pathologies, and Regulations
• Escaping the KL Agreement Trap in On-Policy Distillation
• Qwen3 Technical Report
• Less is More: Early Stopping Rollout for On-Policy Distillation

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection