Skill-R1: Agent Skill Evolution via Reinforcement Learning

Yash Vishe, Rohan Surana, Xunyi Jiang, Zihan Huang, Xintong Li, Nikki Lijing Kuang, Tong Yu, Ryan A. Rossi, Jingbo Shang, Julian McAuley, Junda Wu
May, 2026
PDF
Type
Preprint
Publication
arXiv preprint, 2026

Skill-R1 trains a small generator to improve reusable natural-language procedures while keeping the task model fixed. Feedback from successive rollouts guides skill revisions, enabling adaptation with both open and closed models.

Reinforcement Learning LLM Agents
Xunyi Jiang
Xunyi Jiang
PhD in CS @ 🇺🇸NYU
MS in CS @ 🇺🇸UCSD
BS in DS @ 🇨🇳SUSTech

I am interested in LLM Evaluation, Generative Engine Optimization, Human-AI collaboration, AI for creativity🎻.