SkillZip：透過發現可重用結構，實現免評估技能壓縮以支援自我演化智能體

摘要

自我演化智能體透過附加成功流程與失敗修正來累積可重用技能。隨著時間推移，同一需求常在多個分支、示例與警告中被重複表述，而常見動作序列被複製而非重用。由此產生的技能變得注入成本高昂且難以維護。通用提示壓縮不適合此情境，因為技能並非一段平面文本：其名稱與描述定義了適用時機，其工作流程控制執行，其工具與輸出契約約束有效性，而且即使沒有抽樣任務觸發，罕見例外仍可能至關重要。評估引導式壓縮可以測試這些行為，但它引入了推演（rollouts）、成本，以及對壓縮時評估集的依賴。我們提出 SkillZip，一種免評估方法，透過尋找技能最短且忠實的結構化解釋來壓縮技能。其直覺是「一次解釋，多處引用」：將重複規則在其適用作用域內陳述一次，將重複的動作序列抽取為共享程序，並只保留差異作為明確例外。我們將此直覺形式化為一個型別化最小描述長度目標，作用於技能契約與殘差，並對每個抽取出的觸發條件、工作流邊、工具需求、義務與輸出欄位施加硬性覆蓋約束。該公式提供簡單的共享閾值，在構造上保留獨特且罕見的規則，並支援高效能的局部更新。SkillZip 具有一次性模式，只需一次結構化提取呼叫與確定性最佳化；以及持續的 Zip-on-Write 模式，可整合每個自我演化補丁，而無需重播任務或重新解析完整歷史。透過全面的實驗評估，我們展示了 SkillZip 在壓縮效能、泛化能力與成本開銷方面的有效性與優越性。

English

Self-evolving agents accumulate reusable skills by appending successful procedures and failure fixes. Over time, the same requirement is often restated in several branches, examples, and warnings, while common action sequences are copied rather than reused. The resulting skill becomes expensive to inject and difficult to maintain. Generic prompt compression is ill-suited to this setting because a skill is not a flat passage: its name and description define when it applies, its workflow controls execution, its tool and output contracts constrain validity, and rare exceptions may remain essential even when no sampled task activates them. Evaluation-guided compression can test these behaviors, but it introduces rollouts, cost, and dependence on the compression-time evaluation set. We present SkillZip, an evaluation-free method that compresses a skill by finding its shortest faithful structural explanation. The intuition is explain once, reference many: state a repeated rule once at the scope where it applies, factor a repeated action sequence into a shared procedure, and keep only the differences as explicit exceptions. We formalize this intuition as a typed minimum description-length objective over a skill contract and a residual, subject to a hard coverage constraint for every extracted trigger, workflow edge, tool requirement, obligation, and output field. The formulation provides simple sharing thresholds, preserves unique rare rules by construction, and supports efficient local updates. SkillZip has a one-shot mode with one structured extraction call and deterministic optimization, and a continual Zip-on-Write mode that integrates each self-evolution patch without replaying tasks or reparsing the full history. Through comprehensive experimental evaluations, we demonstrate the effectiveness and superiority of SkillZip in compression performance, generalizability, and cost overhead.