從技能文本到技能結構：代理技能的排程-結構-邏輯表徵法

摘要

大型語言模型代理日益依賴可重複使用的技能——這種能力封裝包結合了指令、控制流程、約束條件和工具調用。然而在當前大多數代理系統中，技能仍以文本密集型構件的形式呈現，包括SKILL.md風格文檔和結構化記錄，其機器可用的實證信息大多仍嵌於自然語言描述中。這對以技能為核心的代理系統構成挑戰：管理技能集合與運用技能支持代理運作，都需要對調用接口、執行結構和具體副作用進行推理，而這些要素往往交織在單一文本表層中。因此，技能知識的顯式表徵可能有助於機器更易獲取和利用這些構件。借鑑尚克和艾伯森在語言知識表徵方面的經典工作——記憶組織包、腳本理論及概念依賴理論，我們提出了首個能分離技能層級調度信號、場景層級執行結構及邏輯層級動作與資源使用實證的代理技能構件結構化表徵方法：調度-結構-邏輯（SSL）表徵框架。我們基於LLM規範化器實例化SSL框架，並在技能發現與風險評估兩項任務的技能語料庫上進行評估，結果顯著優於純文本基準模型：技能任務中MRR從0.573提升至0.707；風險評估任務中宏觀F1值從0.744提升至0.787。這些發現表明，具備顯式且源頭可溯的結構化表徵能使代理技能更易於檢索與審查。同時說明SSL框架應被視作實現更可檢視、可複用且具操作可行性的代理系統技能表徵的實踐性進展，而非最終標準或端到端的技能管理使用機制。

English

LLM agents increasingly rely on reusable skills, capability packages that combine instructions, control flow, constraints, and tool calls. In most current agent systems, however, skills are still represented by text-heavy artifacts, including SKILL.md-style documents and structured records whose machine-usable evidence remains embedded largely in natural-language descriptions. This poses a challenge for skill-centered agent systems: managing skill collections and using skills to support agent both require reasoning over invocation interfaces, execution structure, and concrete side effects that are often entangled in a single textual surface. An explicit representation of skill knowledge may therefore help make these artifacts easier for machines to acquire and leverage. Drawing on Memory Organization Packets, Script Theory, and Conceptual Dependency from Schank and Abelson's classical work on linguistic knowledge representation, we introduce what is, to our knowledge, the first structured representation for agent skill artifacts that disentangles skill-level scheduling signals, scene-level execution structure, and logic-level action and resource-use evidence: the Scheduling-Structural-Logical (SSL) representation. We instantiate SSL with an LLM-based normalizer and evaluate it on a corpus of skills in two tasks, Skill Discovery and Risk Assessment, and superiorly outperform the text-only baselines: in Skill Discovery, SSL improves MRR from 0.573 to 0.707; in Risk Assessment, it improves macro F1 from 0.744 to 0.787. These findings reveal that explicit, source-grounded structure makes agent skills easier to search and review. They also suggest that SSL is best understood as a practical step toward more inspectable, reusable, and operationally actionable skill representations for agent systems, rather than as a finished standard or an end-to-end mechanism for managing and using skills.

從技能文本到技能結構：代理技能的排程-結構-邏輯表徵法

From Skill Text to Skill Structure: The Scheduling-Structural-Logical Representation for Agent Skills

摘要

Support