SkillZip：面向可擴展智能體技能庫的契約保留圖壓縮

摘要

大型語言模型（LLMs）日益作為智能體運作，其程序性知識以可重用的技能套件形式儲存，並在推論時載入。隨著技能庫不斷增長，一個核心挑戰是如何在有限的上下文預算下，暴露最小且充分的可執行上下文。現有系統難以在整個技能層級之下重用常規流程、在壓縮過程中保持程序契約、確保留壓縮後的常規流程可執行且可擴展，以及隨著技能演進而更新壓縮庫。這些挑戰揭示了一個單元錯配：技能以套件形式被檢索，以文字形式被壓縮，並在檢索後才轉換為執行圖，而可靠的復用需要一個承載契約的程序單元。我們提出 SkillZip，一個執行感知的程序抽象框架，它在區段級圖上執行保持契約的壓縮。SkillZip 將重複出現的契約有效模式改寫為可逆的移植宏，同時保留邊界簽名、依賴閉包、驗證器可達性及源級擴展。在推論時，它水合出一個緊湊且依賴閉合的上下文，並僅在需要時展開宏。ReZip 進一步整合新技能，並利用執行證據修訂高風險宏。在技術與具身智能體基準上的綜合實驗表明，SkillZip 持續優於最強基線多達 12.2 個百分點，同時實現 3.46 倍壓縮比、99.2% 的依賴保持率與 98.7% 的驗證器可達率。擴展性分析進一步確認了在 200 至 100K 技能庫範圍內的穩健檢索能力。

English

Large Language Models (LLMs) increasingly act as agents whose procedural knowledge is stored in reusable skill packages and loaded at inference time. As skill libraries grow, a central challenge is to expose the smallest sufficient executable context under a limited context budget. Existing systems struggle to reuse routines below the whole-skill level, preserve procedural contracts during compression, keep compressed routines executable and expandable, and update the compressed library as skills evolve. These challenges reveal a unit mismatch: skills are retrieved as packages, compressed as text, and converted into execution graphs only after retrieval, whereas reliable reuse requires a contract-bearing procedural unit. We propose SkillZip, an execution-aware procedural abstraction framework that performs contract-preserving compression over section-level graphs. SkillZip rewrites recurring contract-valid motifs into reversible ported macros while preserving boundary signatures, dependency closure, verifier reachability, and source-level expansion. At inference time, it hydrates a compact, dependency-closed context and expands macros only when required. ReZip further integrates new skills and revises risky macros using execution evidence. Comprehensive experiments1 on technical and embodied agent benchmarks show SkillZip consistently outperforms the strongest baseline by up to 12.2 points, while achieving a 3.46x compression ratio with 99.2% dependency preservation and 98.7% verifier reachability. Scaling analyses further confirm robust retrieval across skill libraries ranging from 200 to 100K skills.