让大模型自动组合技能完成复杂任务，一次生成最优执行顺序。
Generative Skill Composition for LLM Agents
- 将技能选择、数量和顺序联合建模为序列生成问题。
- 在两个真实编码代理上提升任务通过率23.1%和18.2个百分点。
- 适合需要自动化任务规划的智能体开发人员使用。
近期的大语言模型智能体依赖技能来解决复杂任务。技能是模块化的程序知识包，如搭建沙箱环境、运行测试套件或跨文件重构函数。随着技能库增长并跨任务复用，如何选择合适的技能组合成为核心瓶颈。现有方法要么暴露全部技能供推理，要么通过嵌入或LLM重排序检索技能，但均忽略技能组合的结构性——即需同时决定激活哪些技能、数量多少、执行顺序。本文提出结构化技能组合：给定任务与技能库，预测一个联合指定激活子集、数量与执行顺序的可执行技能计划。我们构建了基于真实人工标注技能库的任务-组合配对训练集。实验显示，SkillComposer在保留测试集上表现优异，并在SkillsBench评测中，使GPT-5.2-Codex与Gemini-3-Pro-Preview的通过率分别提升23.1%、18.2个百分点，超越前3名检索方法，且以更低提示词成本达到黄金检索上限。
原文摘要 · Abstract (English)
Recent LLM agents benefit from skills for solving complex tasks. Skills encapsulate modular packages of procedural knowledge and instructions for performing specialized tasks, such as setting up a sandboxed environment, running a test suite, or refactoring a function across multiple files. As skill libraries grow and become reusable across tasks and domains, selecting an appropriate skill composition has emerged as a central bottleneck. Existing approaches fall into two categories. One exposes the agent's reasoning to the entire skill collection; the other performs skill retrieval via embeddings or LLM-based rerankers. Both provide useful insights; however, they miss the structural nature of skill composition, which is a joint decision over which skills, how many, and in what order -- three dimensions that cannot be decoupled. We formalize this as structured skill composition: given a task and a skill library, predict an executable skill plan that jointly specifies the activated subset, count, and execution order. We propose SkillComposer, which instantiates structured skill composition as task-conditioned skill sequence prediction. SkillComposer uses a constrained autoregressive decoder over skill identifiers, so subset, count, and order emerge jointly from a single decoding pass, and dependencies between successive skills are captured naturally. We build a training set of task-composition pairs from a real, human-curated skill library. We then evaluate SkillComposer along two axes: composition quality on a held-out test set, and downstream task success on SkillsBench across two production-grade coding agents. On GPT-5.2-Codex, Gemini-3-Pro-Preview, SkillComposer raises the pass rate by +23.1, +18.2pp over the no-skill baseline, surpassing top-3 retrieval and matching the gold-skill retrieval upper bound at lower prompt-token cost.
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。