Divergence-Routed On-Policy Distillation for Language Models
cs.AI
Submitted: 2026-10-14
Updated: 2026-10-14
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
- Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
- Measuring Mathematical Problem Solving With the MATH Dataset
- Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
- DASH: Divergence-Adaptive Supervision Horizons for On-Policy Self-Distillation of Reasoning Models
- Reinforcement Learning via Self-Distillation
- Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level
- Entropy-Aware On-Policy Distillation of Language Models
- Scaling Reasoning Efficiently via Relaxed On-Policy Distillation
- Solving Quantitative Reasoning Problems with Language Models
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation
- When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning
- Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
- KL for a KL: On-Policy Distillation with Control Variate Baseline
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- HybridFlow: A Flexible and Efficient RLHF Framework
- STEPS: Selective On-Policy Self-Distillation for Reasoning
- TIP: Token Importance in 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
- Agents' Last Exam
- 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