**摘要**
通过重复使用\ emph {skills} --从过去的经验中提炼的结构化程序工件，语言代理人越来越多地得到改进。特别是\ emph {domain-level}和\ emph {model-generated}技能特别有前途。它们通过编码特定领域的重复过程，在一个领域内提供快速的适应性，并且它们超越了劳动密集型的手工制作。然而，当萃取冰毒
👤 作者: Zisu Huang, Jingwen Xu, Yifan Yang, Ziyang Gong, Qihao Yang, Muzhao Tian, Xiaohua Wang, Changze Lv, Xuemei Gao, Qi Dai, Bei Liu, Kai Qiu, Xue Yang, Dongdong Chen, Xiaoqing Zheng, Chong Luo

---
🔗 **[From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills](https://arxiv.org/abs/2605.23899v1)**

> From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-05-26 08:01