让大模型技能跨平台稳定运行，提升效率与兼容性
SkVM: Revisiting Language VM for Skills across Heterogenous LLMs and Harnesses
- 将技能视为代码，用编译思想实现跨模型兼容
- 任务完成率显著提升，令牌消耗降低40%，延迟减少19-50倍
- 适合多模型协作的智能体系统开发者使用
大型语言模型（LLM）代理日益采用技能作为可复用的组合单元。然而，现有系统将技能当作原始上下文处理，导致同一技能在不同代理平台上表现不一，削弱了技能的可移植性与执行效率。为解决此问题，我们分析了118,000个技能，并借鉴传统编译器设计思想，将技能视为代码，将LLM视为异构处理器。为实现可操作的可移植性，我们把技能需求分解为一组基础能力，并量化各模型-框架组合对这些能力的支持程度。基于能力画像，提出SkVM——一个面向可移植、高效技能执行的编译与运行时系统。编译阶段完成基于能力的编译、环境绑定和并发提取；运行时采用JIT代码固化与自适应重编译进行性能优化。我们在八种不同规模的LLM和三种代理框架上评估，覆盖SkillsBench及代表性技能任务。结果表明，SkVM显著提升跨模型与环境的任务完成率，令牌消耗最高降低40%；性能方面，速度提升达3.2倍，通过代码固化实现19–50倍延迟下降。
原文摘要 · Abstract (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。