机构
*
Cornell University(康奈尔大学)
;
The Hong Kong University of Science and Technology(香港科技大学)
;
The Ohio State University(俄亥俄州立大学)
;
Hong Kong Baptist University(香港浸会大学)
Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation
通过经验知识集成与激活推动LLM工具调用极限
Yupu Hao, Zhuoran Jin, Huanxuan Liao, Kang Liu, Jun Zhao
机构
*
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所复杂系统认知与决策智能重点实验室)
;
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
当较低权限足够时:探究LLM代理中的过度权限工具选择
Kaiyue Yang, Yuyan Bu, Jingwei Yi, Yuchi Wang, Biyu Zhou, Juntao Dai, Songlin Hu, Yaodong Yang
机构
*
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所)
;
Beijing Academy of Artificial Intelligence(北京人工智能研究院)
;
The Chinese University of Hong Kong(香港中文大学)
;
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)
;
School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院)
SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces
SkillFuzz: 面向开放技能市场中隐式意图发现的技能组合模糊测试
Jinwei Hu, Yi Dong, Youcheng Sun, Xiaowei Huang
机构
*
School of Computer Science and Informatics, University of Liverpool(利物浦大学计算机科学与信息学学院)
;
Mohamed bin Zayed University of Artificial Intelligence(穆罕默德·本·扎耶德人工智能大学)
机构
*
Artificial Intelligence Graduate School, Ulsan National Institute of Science and Engineering(人工智能研究生院,乌山科学与工程研究院)
;
Department of Computer Science and Engineering, Ulsan National Institute of Science and Engineering(计算机科学与工程系,乌山科学与工程研究院)
When Does Tool Use Increase the Expressive Power of Finite-Precision Recurrent Models?
工具使用何时会增强有限精度循环模型的表达能力?
Nikola Zubić, Qian Li, Yuyi Wang, Davide Scaramuzza
机构
*
Robotics and Perception Group University of Zurich(机器人感知组苏黎世大学)
;
Shenzhen International Center for Industrial and Applied Mathematics(深圳国际工业与应用数学中心)
;
Shenzhen Research Institute of Big Data(深圳大数据研究 institute)
;
Tengen Intelligence Institute CRRC Zhuzhou Institute(腾云智能研究院 CRRC 长沙研究所)
Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Training
通过训练期间回收零方差查询实现智能体搜索的有效强化学习
João Coelho, João Magalhães, Bruno Martins, Chenyan Xiong
机构
*
Language Technologies Institute, Carnegie Mellon University(卡内基梅隆大学语言技术研究所)
;
Instituto Superior Técnico and INESC-ID, University of Lisbon(里斯本大学理工学院和INESC-ID)
;
NOVA LINCS, NOVA School of Science and Technology(NOVA科学与技术学院LINCS)