SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Zhengxi Lu, Zhiyuan Yao, Jinyang Wu, Chengcheng Han, Qi Gu et al.|April 2, 2026arXiv

Key Takeaway

You can train agents to permanently learn skills rather than retrieve them at runtime, reducing token overhead and improving zero-shot performance by progressively withdrawing skill context during training.

Summary

SKILL0 teaches language model agents to internalize skills (procedural knowledge packages) directly into their parameters through a curriculum that gradually removes skill context during training.

training agents reasoning

Key Terms

skill-internalization curriculum-learning zero-shot-autonomous-behavior dynamic-curriculum agentic-reinforcement-learning