Beyond Passive Imitation: On-Policy Mid-Training Distillation for Language Models
cs.CL, cs.LG
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/ShuidiH20/OPMD
Terminology
Sources
- Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation
- Reinforcement Pre-Training
- The Llama 3 Herd of Models
- SpecOPD: Branch-Parallel On-Policy Distillation for Speculative Decoding
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Qwen3 Technical Report
- MegaMath: Pushing the Limits of Open Math Corpora
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data