An RL View of OPD: Least Square Policy Distillation for Sample-Efficient LLM Reasoning
cs.LG
Submitted: 2026-09-28
Updated: 2026-09-28
Code: https://github.com/UNCSciML/LSPD
Terminology
Sources
- Evaluating Large Language Models Trained on Code
- Rethinking On-Policy Distillation of Large Language Models II: One Training Example
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Soft Actor-Critic Algorithms and Applications
- Measuring Massive Multitask Language Understanding
- Measuring Mathematical Problem Solving With the MATH Dataset
- Distilling the Knowledge in a Neural Network
- Entropy-Aware On-Policy Distillation of Language Models
- On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents
- Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
- GPQA: A Graduate-Level Google-Proof Q&A Benchmark
- Equivalence Between Policy Gradients and Soft Q-Learning
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert Feedback
- Trust Region On-Policy Distillation
- Qwen3 Technical Report
- Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
- When EOS Tokens Disagree: Understanding Length Inflation 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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks