Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.27488 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915970527789056 |
|---|---|
| author | Tian, Yu Chen, Jiawei Zheng, Lifan Tao, Mingxiang Zeng, Xinyi Yin, Zhaoxia Su, Hang Sun, Xian |
| author_facet | Tian, Yu Chen, Jiawei Zheng, Lifan Tao, Mingxiang Zeng, Xinyi Yin, Zhaoxia Su, Hang Sun, Xian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_27488 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO Tian, Yu Chen, Jiawei Zheng, Lifan Tao, Mingxiang Zeng, Xinyi Yin, Zhaoxia Su, Hang Sun, Xian Computation and Language 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. |
| title | Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.27488 |