研究人员推出了一种名为技能检索增强（SRA）的新方法，用于增强代理式AI系统。SRA允许代理从大型外部语料库中动态检索和应用技能，克服了在上下文窗口中枚举技能的局限性。为了评估这种方法，该论文提出了SRA-Bench，这是一个包含5,400个测试实例和26,262个技能的技能语料库的基准。实验表明，SRA显著提高了代理性能，尽管基础模型在确定何时加载技能的能力方面仍存在差距。 AI
影响 引入了一种新的代理式AI技能管理范式，有望提高可扩展性和性能。
排序理由 这是一篇介绍代理式AI新方法和基准的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2604.24594v1 Announce Type: new Abstract: As large language models (LLMs) evolve into agentic problem solvers, they increasingly rely on external, reusable skills to handle tasks beyond their native parametric capabilities. In existing agent systems, the dominant strategy f…
As large language models (LLMs) evolve into agentic problem solvers, they increasingly rely on external, reusable skills to handle tasks beyond their native parametric capabilities. In existing agent systems, the dominant strategy for incorporating skills is to explicitly enumera…