动态调整技能注入的上下文，让大模型代理更聪明地用技能完成任务。
SkillsInjector: Dynamic Skill Context Construction for LLM Agents
- 根据任务动态选择技能数量和内容，不再固定预算。
- 通过上下文重排提升技能描述的协同效果，性能提升7.3%。
- 适合构建复杂任务的智能代理系统，尤其在多技能协作场景中。
大模型代理依赖不断扩大的技能库来处理复杂任务，但增加技能并不总能提升表现，甚至可能降低效率。现有方法仍将技能注入视为静态过程：使用固定标准选择技能、提前设定预算、保持描述不变。我们认为，技能的暴露方式、数量及呈现形式都会影响下游性能。为此，我们提出SkillsInjector，一种两阶段自适应方法：首先，上下文规划器学习基于执行反馈的技能偏好，并为每项任务自适应地确定技能数量；其次，集合感知渲染器调整所选技能描述的呈现方式，使其与共注入的其他技能形成更好协同。在tau2-bench、SkillsBench和ALFWorld上，SkillsInjector均取得最高得分，分别比最强基线提升3.9、6.1和7.3个百分点。消融实验表明，技能选择、自适应预算和集合感知渲染各自贡献了性能增益。结果表明，优化技能注入的上下文本身，可显著提升技能增强型代理的表现。代码将在发表后公开。
原文摘要 · Abstract (English)
LLM agents now draw on growing skill libraries to handle complex tasks. However, injecting more skills does not always improve task completion and can even degrade it. Existing methods still treat skill injection as a static step, selecting skills with fixed criteria, fixing the budget in advance, and leaving descriptions unchanged. We argue that this static treatment can undermine the utility of skills, because which skills are exposed, how many are included, and how they are presented all affect downstream performance. We propose SkillsInjector, a two-stage adaptive method that jointly addresses these decisions. First, a context planner learns execution-grounded skill preferences and admits an adaptive number of skills for each task. A set-aware renderer then tailors how selected descriptions are presented relative to their co-injected neighbors. Across tau2-bench, SkillsBench, and ALFWorld, SkillsInjector achieves the highest score, improving over the strongest baseline by 3.9, 6.1, and 7.3 percentage points, respectively. Ablation studies show that skill selection, adaptive budgeting, and set-aware rendering each contribute to the gain. These results show that skill-augmented agents benefit from optimizing the injected context itself. Code will be released upon publication
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。