When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents
何时不应模仿:面向可靠工具使用大语言模型智能体的边界感知技能记忆
Zihan Lin, Zhenyu Chen, Jiawen Wei, Xiaohan Wang, Jie Cao, Jiajun Chai, Wei Lin, Guojun Yin, Ran He
机构
*
Meituan(美团)
;
School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉科学学院)
;
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)
;
Zhongguancun Academy(中关村学院)
机构
*
Nankai University(南开大学)
;
National University of Singapore(新加坡国立大学)
;
Shanghai Institute of Optics and Fine Mechanics, Chinese Academy of Sciences(中国科学院上海光学精密机械研究所)
;
Peking University(北京大学)
;
Technical University of Munich(慕尼黑工业大学)
;
Queen Mary University of London(伦敦大学玛丽女王学院)
;
Wuhan University(武汉大学)
;
University of New South Wales(新南威尔士大学)
机构
*
School of Computing Science, University of Glasgow, UK(格拉斯哥大学计算机科学学院)
;
School of Natural and Computing Science, University of Aberdeen, UK(阿伯丁大学自然与计算科学学院)
Comments3 pages, 2 figures, Adjunct Proceedings of the 39th Annual ACM Symposium on User Interface Software and Technology (UIST '26 Adjunct), Detroit, MI, USA