Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning
Paper • 2608.05139 • Published • 25
Yang Yongjin
Dragonjinny
AI & ML interests
Reinforcement Learning, Self-Improvement, Open-endedness, Generative AI
Recent Activity
submitted a paper about 1 month ago
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR upvoted a paper about 1 month ago
Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVROrganizations
None yet