Pass the Baton: Trajectory-Relayed On-Policy Distillation
cs.CL, cs.AI
Submitted: 2026-07-28
Updated: 2026-11-15
Code: https://github.com/zju-real/Relay-OPD
Project page: https://zju-real.github.io/Relay-OPD
Terminology
Sources
- Accelerating Large Language Model Decoding with Speculative Sampling
- Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Measuring Mathematical Problem Solving With the MATH Dataset
- Distilling the Knowledge in a Neural Network
- Reinforcement Learning via Self-Distillation
- OpenAI o1 System Card
- Trajectory-Refined Distillation
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- Privileged Information Distillation for Language Models
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Self-Distillation Enables Continual Learning
- MiMo-V2-Flash Technical Report
- On the Position Bias of On-Policy Distillation
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Qwen3 Technical Report
- Black-Box On-Policy Distillation of Large Language Models
- GLM-5: from Vibe Coding to Agentic Engineering
- Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models
- Less is More: Early Stopping Rollout for On-Policy Distillation
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