MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
Paper • 2606.30406 • Published • 25
Distillation
-
-
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training
Paper • 2607.05804 • Published • 20 -
Trust Region Policy Distillation
Paper • 2607.04751 • Published • 36 -
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Paper • 2607.14777 • Published • 106 -
ShortOPD: Recovering Pruned LLMs with Short-to-Long On-Policy Distillation
Paper • 2607.13124 • Published • 20 -
Visual Contrastive Self-Distillation
Paper • 2607.21556 • Published • 52 -
From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search
Paper • 2607.24280 • Published • 83 -
Pass the Baton: Trajectory-Relayed On-Policy Distillation
Paper • 2607.26057 • Published • 33 -
Enhancing Rubric-based RL via Self-Distillation
Paper • 2607.18082 • Published • 25 -
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Paper • 2608.05987 • Published • 100 -
Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory
Paper • 2608.07169 • Published • 50 -
SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation
Paper • 2608.04419 • Published • 28 -
Self-Supervised Visual On-Policy Distillation
Paper • 2608.14144 • Published • 170 -
Latent On-Policy Self-Distillation
Paper • 2608.13040 • Published • 25 -
SimpleOPD: Simple Tokenizer-Agnostic On-Policy Distillation for Long-Context Reasoning
Paper • 2608.14277 • Published • 35 -
D^3-MOPD: Adaptive Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation
Paper • 2608.24987 • Published • 22