AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning
Paper • 2608.05987 • Published • 104 •
3
yan
Nikoyan
·
AI & ML interests
LLM,RL,Agent
Recent Activity
upvoted a paper about 1 month ago
Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting upvoted a paper about 1 month ago
TCAndon-Router: Adaptive Reasoning Router for Multi-Agent Collaboration authored a paper about 1 month ago
SkillEvo: Self-Renewing Evolution Gradients from Multi-Turn Interaction FeedbackOrganizations
commented 2
papers about 2 months ago