Skill-R1: Agent Skill Evolution via Reinforcement Learning

ArXi:2605.09359v1 Announce Type: cross Agentic large language models often rely on skills, reusable natural language procedures that guide planning, action, and tool use. In practice, skills are typically improved through prompt engineering or by aligning the task LLM itself, which is costly, model-specific, and often infeasible for closed-source models.