提出智能体技能的系统化框架，解决长期任务中的可复用能力问题。
SoK: Agentic Skills -- Beyond Tool Use in LLM Agents
- 构建七种技能设计模式，涵盖从代码到自演化库的多种实现方式。
- 实证发现：精心筛选的技能可显著提升智能体成功率，自动生成的可能降低表现。
- 揭示技能市场安全风险，案例显示近1200个恶意技能曾大规模窃取敏感信息。
智能体系统日益依赖可复用的程序化能力（即‘技能’）来可靠执行长周期工作流。这些技能是封装了适用条件、执行策略、终止标准和可复用接口的可调用模块，能跨任务稳定运行。本文全面梳理技能在发现、训练、提炼、存储、组合、评估与更新全生命周期中的作用，并提出两个互补分类体系：一是系统级七种设计模式，涵盖元数据驱动渐进披露、可执行代码技能、自演化库及市场分发等；二是‘表示×范围’分类法，描述技能形式（自然语言、代码、策略、混合）及其运行环境（网络、操作系统、软件工程、机器人）。分析了技能型代理的安全与治理挑战，包括供应链风险、通过技能载荷的提示注入攻击，以及分层信任执行机制，基于ClawHavoc事件案例——近1200个恶意技能入侵主流代理市场，大规模窃取API密钥、加密货币钱包和浏览器凭据。进一步调研确定性评估方法，近期基准证据表明，经筛选的技能能显著提高智能体成功率，而自生成技能可能造成性能下降。最后指出迈向真实世界自主代理所需的鲁棒、可验证、可认证技能的开放挑战。
原文摘要 · Abstract (English)
Agentic systems increasingly rely on reusable procedural capabilities, \textit{a.k.a., agentic skills}, to execute long-horizon workflows reliably. These capabilities are callable modules that package procedural knowledge with explicit applicability conditions, execution policies, termination criteria, and reusable interfaces. Unlike one-off plans or atomic tool calls, skills operate (and often do well) across tasks. This paper maps the skill layer across the full lifecycle (discovery, practice, distillation, storage, composition, evaluation, and update) and introduces two complementary taxonomies. The first is a system-level set of \textbf{seven design patterns} capturing how skills are packaged and executed in practice, from metadata-driven progressive disclosure and executable code skills to self-evolving libraries and marketplace distribution. The second is an orthogonal \textbf{representation $\times$ scope} taxonomy describing what skills \emph{are} (natural language, code, policy, hybrid) and what environments they operate over (web, OS, software engineering, robotics). We analyze the security and governance implications of skill-based agents, covering supply-chain risks, prompt injection via skill payloads, and trust-tiered execution, grounded by a case study of the ClawHavoc campaign in which nearly 1{,}200 malicious skills infiltrated a major agent marketplace, exfiltrating API keys, cryptocurrency wallets, and browser credentials at scale. We further survey deterministic evaluation approaches, anchored by recent benchmark evidence that curated skills can substantially improve agent success rates while self-generated skills may degrade them. We conclude with open challenges toward robust, verifiable, and certifiable skills for real-world autonomous 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。