为大模型智能体设计可复用的行为技能架构，提升系统可控性与可追溯性。
Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agents
- 提出十种技能使用架构模式，分核心与辅助两类
- 构建四层参考架构，涵盖供应、中介、控制与反馈责任
- 在8个系统中验证，支持技能的发现、执行与证据留存
智能体技能将可复用的行为知识和指导以持久化成果形式外化，供大模型智能体发现、激活与解析。尽管技能在静态时无行为，但其架构职责在运行时显现：技能被选中后，绑定上下文与权限约束，由随机智能体解释，并记录为运行证据。这种特定运行中的关联称为“技能使用”。本文研究技能的利用：管理从技能成果到技能使用的过渡，约束使用带来的执行后果，并记录用于归属、验证、修复与演进的证据。论文提出十种基于实证的架构模式（五种核心，五种支持），并整合为包含四个责任层的参考架构：供应链、中介、执行控制、证据与反馈。通过跨系统实例化在8个选定系统中评估该架构。这些模式与参考架构为分析各类智能体系统的技能利用责任提供了术语体系与诊断框架。
原文摘要 · Abstract (English)
Agent skills externalise reusable agent-facing behavioural knowledge and guidance as persistent artefacts that can be discovered, activated, and interpreted by LLM agents. Although a skill artefact is static at rest, its architectural responsibilities arise in use, when the artefact is selected for a run, bound to context and authority constraints, interpreted by a stochastic agent, and recorded as run evidence. We call this run-specific relation skill-in-use. This paper studies agent skill harnessing: the architectural responsibilities that govern the transition from skill artefacts to skill-in-use, bound the executable consequences associated with skill-in-use, and capture evidence for attribution, verification, repair, and evolution. This paper provides a catalogue of ten empirically grounded architectural patterns (five core, five supporting) for skill harnessing and synthesises them into a reference architecture with four responsibility layers: Supply Chain, Mediation, Execution Control, and Evidence & Feedback. We evaluate the architecture through cross-instantiation across 8 selected systems. The resulting patterns and reference architecture provide a vocabulary and diagnostic frame for analysing skill-harnessing responsibilities across agent systems.
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。