SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning
Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions, leaving a supervision gap between episode-level outcomes and token-level policy learning. We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills and dis
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%sgl-project/sglang →
“Shared author/contributor keys: luo”
- FuzzySimilar title/name (fuzzy) · 59%Fosowl/agenticSeek →
“Fuzzy title match (0.73): “SEED: Self-Evolving On-Policy Distillation for Agentic Reinf” ≈ “Fosowl/agenticSeek””
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “SEED: Self-Evolving On-Policy Distillation for Agentic Reinf” ≈ “aymericdamien/TopDeepLearning””
- LinkedLinked via arxiv author · 85%Jinyang Wu →
“SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning”
- LinkedLinked via arxiv author · 85%Shuo Yang →
“SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning”
- LinkedLinked via arxiv author · 85%Zhengxi Lu →
“SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning”
- LinkedLinked via arxiv author · 85%Yifan Zhang →
“SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning”
- LinkedLinked via arxiv author · 85%Yuhao Shen →
“SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning”