发表机构
UNSW; CSIRO（新南威尔士大学; 联邦科学与工业研究组织）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SkillZip是一种执行感知的过程抽象框架，通过对节级图进行保留契约的压缩，解决了智能体技能库的可扩展问题，在基准测试中优于基线，实现了高压缩率和稳健检索。
AI 中文摘要
大型语言模型（LLMs）越来越多地充当智能体，其过程知识存储在可重用的技能包中，并在推理时加载。随着技能库的增长，核心挑战是在有限的上下文预算下暴露最小的足够可执行上下文。现有系统难以在整个技能级别以下重用例程、在压缩过程中保留过程契约、保持压缩后的例程可执行且可扩展，以及在技能演变时更新压缩后的库。这些挑战揭示了单位不匹配：技能作为包被检索、作为文本被压缩，并且仅在检索后才转换为执行图，而可靠的重用需要带有契约的过程单元。我们提出SkillZip，这是一个执行感知的过程抽象框架，它对节级图执行保留契约的压缩。SkillZip将重复出现的契约有效 motifs 重写为可逆的移植宏，同时保留边界签名、依赖闭包、验证器可达性和源级可扩展性。在推理时，它生成紧凑的、依赖闭包的上下文，并仅在需要时扩展宏。ReZip进一步使用执行证据集成新技能并修改风险宏。在技术和具身智能体基准上的综合实验表明，SkillZip始终优于最强基线，最高可达12.2个点，同时实现3.46倍的压缩率，具有99.2%的依赖保留率和98.7%的验证器可达性。扩展分析进一步确认了在200到100,000个技能的技能库中检索的稳健性。
英文摘要
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.
