| title | Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO |
|---|---|
| authors | Yu Tian, Jiawei Chen, Lifan Zheng, Mingxiang Tao, Xinyi Zeng, Zhaoxia Yin, Hang Su, Xian Sun |
| date | 2026-04-30 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2604.27488 |
| upvotes | 7 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | We introduce Skills-Coach, a novel automated framework designed to significantly enhance the self-evolution of skills within Large Language Model (LLM)-based agents. Addressing the current fragmentation of the skill ecosystem, Skills-Coach explores the boundaries of skill capabilities, thereby facilitating the comprehensive competency coverage essential for intelligent applications. The framework comprises four core modules: a Diverse Task Generation Module that systematically creates a comprehensive test suite for various skills; a Lightweight Optimization Module dedicated to optimizing skill prompts and their corresponding code; a Comparative Execution Module facilitating the execution and evaluation of both original and optimized skills; and a Traceable Evaluation Module, which rigorously evaluates performance against specified criteria. Skills-Coach offers flexible execution options through its virtual and real modes. To validate its efficacy, we introduce Skill-X, a comprehensive benchmark dataset consisting of 48 diverse skills. Experimental results demonstrate that Skills-Coach achieves significant performance improvements in skill capability across a wide range of categories, highlighting its potential to advance the development of more robust and adaptable LLM-based agents. |
cite
@misc{tian2026skills,
title={Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO},
author={Yu Tian and Jiawei Chen and Lifan Zheng and Mingxiang Tao and Xinyi Zeng and Zhaoxia Yin and Hang Su and Xian Sun},
year={2026},
eprint={2604.27488},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2604.27488}
}