无需训练，自动优化大模型技能，提升智能体能力
Skills-Coach: A Self-Evolving Skill Optimizer via Training-Free GRPO
- 通过无训练的强化学习优化技能提示和代码
- 在48种技能上显著提升能力，覆盖广泛应用场景
- 支持虚拟与真实模式，适合智能体开发与评测
我们提出Skills-Coach，一种新型自动化框架，用于显著提升基于大语言模型（LLM）智能体中技能的自我演化能力。针对当前技能生态碎片化问题，Skills-Coach探索技能能力边界，实现智能应用所需的全面能力覆盖。框架包含四个核心模块：多样任务生成模块，系统构建涵盖多种技能的测试套件；轻量级优化模块，专门优化技能提示及其对应代码；对比执行模块，支持原版与优化后技能的执行与评估；可追溯评估模块，严格依据指定标准进行性能评估。Skills-Coach提供虚拟与真实两种执行模式。为验证有效性，我们构建了包含48种多样化技能的Skill-X基准数据集。实验结果表明，Skills-Coach在多个类别中显著提升技能能力，展现出推动更鲁棒、更适应性LLM智能体发展的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。