MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation

arXiv:2609.30837 · cs.LG, cs.AI · Submitted 2026-09-25 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-25

Updated: 2026-09-28

Code: https://github.com/TURLEing/MOPD-Router

Terminology

• Distillation — 46× in this paper · explained in 2 episodes
• Aggregation — 23× in this paper · explained in 1 episode
• On-Policy Distillation — 21× in this paper · explained in 3 episodes
• Alignment — 20× in this paper · explained in 1 episode
• Benchmark — 14× in this paper · explained in 2 episodes
• Verification — 8× in this paper · explained in 2 episodes
• Ablation — 7× in this paper · explained in 1 episode
• Multi-teacher On-Policy Distillation — 7× in this paper
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Calibration — 5× in this paper · explained in 7 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Self-Distillation — 3× in this paper · explained in 7 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Accuracy — 2× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Process Reinforcement through Implicit Rewards
• GLM-5: from Vibe Coding to Agentic Engineering
• DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
• On-Policy Delta Distillation
• Reinforcement Learning via Self-Distillation
• Entropy-Aware On-Policy Distillation of Language Models
• Kimi K3: Open Frontier Intelligence
• Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
• MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• D cubed-MOPD: Dynamic Domain ScheDuling for Efficient Multi-Teacher Distillation
• Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models
• Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
• Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
• Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation
• MiMo-V2-Flash Technical Report
• DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
• TIP: Token Importance in On-Policy Distillation

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks