让大模型像搭积木一样动态调用技能，提升智能体的可扩展性与安全性
Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward
- 设计可组合的技能包，通过MCP协议按需加载代码与指令
- 发现26.1%的公开技能含漏洞，提出四层权限治理框架
- 聚焦技能生态的架构、获取、部署与安全，适合构建可信智能体的研究者
从单体语言模型转向模块化、技能驱动的智能体，标志着大语言模型（LLM）实际部署方式的根本转变。不再将所有过程知识编码于模型权重中，而是通过可组合的技能包——即按需加载的指令、代码和资源——实现能力的动态扩展，无需重新训练。该范式基于渐进披露、可移植技能定义及与模型上下文协议（MCP）的集成。本文全面梳理了近期快速演进的智能体技能领域，从四个维度展开：(i) 架构基础，分析SKILL.md规范、渐进式上下文加载及技能与MCP的互补作用；(ii) 技能获取，涵盖基于技能库的强化学习、自主技能发现（SEAgent）与组合式技能合成；(iii) 规模化部署，包括计算机使用智能体（CUA）栈、GUI对齐进展，以及OSWorld和SWE-bench上的基准评测；(iv) 安全性，实证分析显示26.1%的社区贡献技能存在漏洞，据此提出技能可信度与生命周期治理框架——一种四级门控权限模型，将技能来源映射至渐进式部署能力。识别出七个开放挑战，如跨平台技能可移植性与基于能力的权限模型，并提出实现可信、自进化技能生态的研究路线图。本工作区别于以往泛化覆盖LLM智能体或工具使用的综述，专注于新兴的技能抽象层及其对下一代代理系统的影响。
原文摘要 · Abstract (English)
The transition from monolithic language models to modular, skill-equipped agents marks a defining shift in how large language models (LLMs) are deployed in practice. Rather than encoding all procedural knowledge within model weights, agent skills -- composable packages of instructions, code, and resources that agents load on demand -- enable dynamic capability extension without retraining. It is formalized in a paradigm of progressive disclosure, portable skill definitions, and integration with the Model Context Protocol (MCP). This survey provides a comprehensive treatment of the agent skills landscape, as it has rapidly evolved during the last few months. We organize the field along four axes: (i) architectural foundations, examining the SKILL$.$md specification, progressive context loading, and the complementary roles of skills and MCP; (ii) skill acquisition, covering reinforcement learning with skill libraries, autonomous skill discovery (SEAgent), and compositional skill synthesis; (iii) deployment at scale, including the computer-use agent (CUA) stack, GUI grounding advances, and benchmark progress on OSWorld and SWE-bench; and (iv) security, where recent empirical analyses reveal that 26.1% of community-contributed skills contain vulnerabilities, motivating our proposed Skill Trust and Lifecycle Governance Framework -- a four-tier, gate-based permission model that maps skill provenance to graduated deployment capabilities. We identify seven open challenges -- from cross-platform skill portability to capability-based permission models -- and propose a research agenda for realizing trustworthy, self-improving skill ecosystems. Unlike prior surveys that broadly cover LLM agents or tool use, this work focuses specifically on the emerging skill abstraction layer and its implications for the next generation of agentic systems. Project repo: https://github.com/scienceaix/agentskills
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。