Distilled Reinforcement Learning for LLM Post-training
Large language model (LLM) post-training is essential for improving reasoning, adaptation, and alignment. Existing methods mainly follow two paradigms: reinforcement learning (RL) and on-policy distillation (OPD). However, RL relies on coarse-grained outcome supervision, resulting in difficult credit assignment and limited capability to acquire new knowledge. OPD, meanwhile, unconditionally matches teacher logits through KL divergence, which creates a dilemma: similar teachers provide little new knowledge, while substantially different teachers often yield ineffective guidance, largely restric
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- FuzzyOverlapping authors or contributors · 62%bytedance/deer-flow →
“Shared author/contributor keys: wang”
- FuzzyOverlapping authors or contributors · 62%ray-project/ray →
“Shared author/contributor keys: wang”
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “Distilled Reinforcement Learning for LLM Post-training” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Yuchen Wang →
“Distilled Reinforcement Learning for LLM Post-training”
- LinkedLinked via arxiv author · 85%Zhaochun Li →
“Distilled Reinforcement Learning for LLM Post-training”
- LinkedLinked via arxiv author · 85%Jionghao Bai →
“Distilled Reinforcement Learning for LLM Post-training”
- LinkedLinked via arxiv author · 85%Yining Zhang →
“Distilled Reinforcement Learning for LLM Post-training”
- LinkedLinked via arxiv author · 85%Hexuan Deng →
“Distilled Reinforcement Learning for LLM Post-training”