AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Paper • 2608.05987 • Published • 100 •
3
yan
Nikoyan
·
AI & ML interests
LLM,RL,Agent
Recent Activity
authored a paper 3 days ago
SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction Feedback commentedon a paper 7 days ago
AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning upvoted a paper 10 days ago
SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction FeedbackOrganizations
commented a
paper 7 days ago
commented a
paper 10 days ago