SkillZip：面向可扩展智能体技能库的契约保留图压缩

AI 摘要

SkillZip 是一种面向大规模智能体技能库的图压缩框架，通过保留契约的图单元压缩可复用技能，在有限上下文预算下实现高效检索与扩展。实验表明，SkillZip 在技术和具身智能体基准上比最强基线最高提升 12.2 分，压缩比达 3.46 倍，依赖保留率 99.2%，验证器可达性 98.7%，并支持从 200 到 10 万技能的库规模扩展。

正文节选

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries Abstract SkillZip compresses reusable procedural skills into contract-preserving, executable graph units to enable efficient retrieval and expansion under limited context budgets. 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 execu

发布时间：—

抓取时间：2026-08-13 19:56

来源机构：Hugging Face