检索增强的技能优化：通过跨框架适配
Retrieval-Augmented Skill Optimization via Cross-Harness Adaptation
- Korea University（高丽大学）
- KAIST（韩国科学技术院）
- Meta AI
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出RASO框架，利用外部技能语料库作为先验知识，通过跨框架适配实现检索增强的技能初始化与更新，在四个基准和两个模型上持续优于基线。
AI中文摘要：
智能体技能是一种可复用的、可操作的自然语言工件，在给定框架下引导智能体有效执行任务。近期研究探索了智能体技能的优化，促进了涵盖多种任务、领域和框架的公开可用技能库的不断增长。尽管已有数百万公开共享的技能，现有技能优化方法大多忽视了这一积累的知识，而是仅依赖昂贵的智能体回放来为目标任务迭代优化技能。为解决这一问题，我们提出检索增强的技能优化（RASO），一个在技能优化全过程中利用外部技能语料库作为先验知识的框架。RASO从现有技能中检索相关知识，并通过跨框架适配将其适应于目标任务和框架，同时考虑领域和框架的不匹配。RASO包含两个互补阶段：检索增强的技能初始化（RASI）在无需智能体回放的情况下构建基于知识的初始技能，而检索增强的技能更新（RASU）通过检索由执行反馈引导的外部知识来迭代优化技能。在四个智能体基准和两个模型上，大量实验表明，RASO在性能上始终优于未使用检索增强技能初始化和更新的基线方法。
英文摘要：
An agent skill is a reusable, actionable natural-language artifact that guides an agent to perform a task effectively under a given harness. Recent studies have explored the optimization of agent skills, contributing to a growing collection of publicly available skills spanning diverse tasks, domains, and harnesses. Despite millions of publicly shared skills, existing skill optimization methods largely overlook this accumulated knowledge, instead relying solely on expensive agent rollouts to iteratively refine skills for a target task. To address this, we propose \textbf{Retrieval-Augmented Skill Optimization (RASO)}, a framework that leverages an external skill corpus as prior knowledge throughout skill optimization. RASO retrieves relevant knowledge from existing skills and adapts it to the target task and harness via Cross-Harness Adaptation, accounting for mismatches in both domain and harness. RASO comprises two complementary stages: \textbf{Retrieval-Augmented Skill Initialization (RASI)} constructs a knowledge-grounded initial skill without requiring agent rollouts, while \textbf{Retrieval-Augmented Skill Update (RASU)} iteratively refines the skill by retrieving external knowledge guided by execution feedback. Across four agent benchmarks and two models, extensive experiments show that RASO consistently outperforms baselines without retrieval-augmented skill initialization and updating.
