SkillSmith：将技能编译为边界引导的运行时接口
SkillSmith: Compiling Agent Skills into Boundary-Guided Runtime Interfaces
AI总结：
SkillSmith通过将技能包编译为最小执行接口，减少运行时冗余，提升效率与准确性。
摘要：
近年来，技能被广泛应用于基于大语言模型（LLM）的代理系统中。现有框架中，技能通常在匹配到运行时任务后注入到代理推理循环中作为上下文引导，使代理具备专门的任务解决能力。我们发现这种执行范式引入了两个主要冗余来源：无关上下文注入和重复的技能特定推理与规划。为此，我们提出了SkillSmith，一种以边界优先的编译器-运行时框架，将技能包离线编译为最小执行接口。通过从技能中提取细粒度的操作边界，SkillSmith使代理能够在运行时动态访问并执行相关组件，从而减少不必要的上下文注入和冗余推理开销。在SkillsBench基准测试中，SkillSmith将求解阶段的token使用量减少了57.44%，思考迭代次数减少了42.99%，求解时间减少了50.57%（2.02倍更快），以及与使用原始技能相比，token比例的货币成本减少了57.44%。此外，由更强模型生成的编译产物可以被较小或更高效的运行时模型重用，在原始技能解释失败的情况下提高任务准确性。源代码和数据可在https://github.com/AetherHeart-AI/Aeloon上获得。
英文摘要：
Recently, skills have been widely adopted in large language model (LLM)-based agent systems across various domains. In existing frameworks, skills are typically injected into the agent reasoning loop as contextual guidance once matched to a runtime task, enabling specialized task-solving capabilities. We find that this execution paradigm introduces two major sources of redundancy: irrelevant context injection and repeated skill-specific reasoning and planning. To this end, we propose SkillSmith, a boundary-first compiler-runtime framework that compiles skill packages offline into minimal executable interfaces. By extracting fine-grained operational boundaries from skills, SkillSmith enables agents to dynamically access and execute only the relevant components at runtime, thereby minimizing unnecessary context injection and redundant reasoning overhead. In the evaluation on SkillsBench benchmark, SkillSmith reduces solve-stage token usage by 57.44%, thinking iterations by 42.99%, solve time by 50.57% (2.02x faster), and token-proportional monetary cost by 57.44% compared with using raw-skills. Moreover, compiled artifacts produced by a stronger model can be reused by a smaller or more efficient runtime model, improving task accuracy in cases where raw skill interpretation fails. The source code and data are available at https://github.com/AetherHeart-AI/Aeloon.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
