AI RESEARCH
SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment
arXiv CS.AI
•
ArXi:2605.27899v1 Announce Type: new Structured skill prompts improve exploration in long-horizon agentic reinforcement learning (RL). Skill-augmented RL methods retain external skills at inference, while skill-internalization RL methods withdraw them during