SkVM：通用高效技能编译执行方案

摘要

随着LLM智能体逐渐将技能作为可复用的组合单元，当前各平台虽能共享技能资源，却普遍将其视为原始上下文处理，导致同一技能在不同智能体间表现不一致。这种脆弱性严重制约了技能的可移植性与执行效率。为解决该问题，我们分析了11.8万个技能，并从传统编译器设计中获得启发：将技能视为代码，将LLM视作异构处理器。为实现可移植性，我们将技能需求解构为基本能力集，并量化评估不同模型-框架组合对这些能力的支持程度。基于此能力画像，我们提出SkVM——专为可移植高效技能执行设计的编译与运行时系统。编译阶段，SkVM执行基于能力的编译、环境绑定和并发提取；运行时则通过JIT代码固化与自适应重编译进行性能优化。我们在8种规模各异的LLM和3类智能体框架上开展评估，覆盖SkillsBench及典型技能任务。实验表明：SkVM能显著提升不同模型与环境下的任务完成率，同时降低最高40%的token消耗；性能方面，通过增强并行性实现3.2倍加速，借助代码固化将延迟降低19-50倍。

English

LLM agents increasingly adopt skills as a reusable unit of composition. While skills are shared across diverse agent platforms, current systems treat them as raw context, causing the same skill to behave inconsistently for different agents. This fragility undermines skill portability and execution efficiency. To address this challenge, we analyze 118,000 skills and draw inspiration from traditional compiler design. We treat skills as code and LLMs as heterogeneous processors. To make portability actionable, we decompose a skill's requirements into a set of primitive capabilities, and measure how well each model-harness pair supports them. Based on these capability profiles, we propose SkVM, a compilation and runtime system designed for portable and efficient skill execution. At compile time, SkVM performs capability-based compilation, environment binding, and concurrency extraction. At runtime, SkVM applies JIT code solidification and adaptive recompilation for performance optimization. We evaluate SkVM across eight LLMs of varying scales and three agent harnesses, covering SkillsBench and representative skill tasks. Results demonstrate that SkVM significantly improves task completion rates across different models and environments while reducing token consumption by up to 40%. In terms of performance, SkVM achieves up to 3.2x speedup with enhanced parallelism, and 19-50x latency reduction through code solidification.

SkVM：通用高效技能编译执行方案

SkVM: Compiling Skills for Efficient Execution Everywhere

摘要

Support