AI Agent

Adaptive Monitoring and Real-World Evaluation of Agentic AI Systems

Manish Shukla

机构 * Independent Researcher（独立研究者） 纠错

专题命中 Agent评测 ：agentic(title,abstract)；agent(abstract)；planning(abstract)；multi-agent(abstract)

VisDocSketcher: Towards Scalable Visual Documentation with Agentic Systems

Luís F. Gomes, Xin Zhou, David Lo, Rui Abreu

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Singapore Management University（新加坡管理学院） ； Faculty of Engineering, University of Porto（葡萄牙波尔图大学工程学院） 纠错

专题命中 Agent评测 ：agentic(title,abstract)；agent(abstract)；分类 cs.AI、cs.SE

Is the `Agent' Paradigm a Limiting Framework for Next-Generation Intelligent Systems?

Jesse Gardner, Vladimir A. Baulin

机构 * Active Inference Institute（主动推断研究所） 纠错

专题命中 Agent评测 ：agent(title,abstract)；agentic(abstract)；分类 cs.AI

What if Virtual Agents Had Scents? Users' Judgments of Virtual Agent Personality and Appeals in Encounters

Dongyun Han, Siyeon Bak, So-Hui Kim, Kangsoo Kim, Sun-Jeong Kim, Isaac Cho

专题命中 Agent评测 ：agent(title,abstract)

Agent-based Simulation for Drone Charging in an Internet of Things Environment System

Leonardo Grando, José Roberto Emiliano Leite, Edson Luiz Ursini

机构 * University of Campinas (UNICAMP)（坎皮纳斯大学） 纠错

专题命中 Agent评测 ：agent(title,abstract)

Comments 4 pages

Survival at Any Cost? LLMs and the Choice Between Self-Preservation and Human Harm

Alireza Mohamadi, Ali Yavari

专题命中 Agent评测 ：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.CL

Comments Preprint. Under review

Imitation Learning as Return Distribution Matching

Filippo Lazzati, Alberto Maria Metelli

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning

Dieter Balemans, Thomas Huybrechts, Jan Steckel, Siegfried Mercelis

机构 * IDLab - Faculty of Applied Engineering, University of Antwerp - imec（IDLab - 工程学院，安特卫普大学 - imec） ； CoSysLab - Faculty of Applied Engineering, University of Antwerp（CoSysLab - 工程学院，安特卫普大学） ； Flanders Make Strategic Research Centre（弗拉芒制造战略研究中心） 纠错

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Online Omniprediction with Long-Term Constraints

Yahav Bechavod, Jiuyao Lu, Aaron Roth

机构 * Department of Computer and Information Sciences, University of Pennsylvania（计算机与信息科学系，宾夕法尼亚大学） ； Department of Statistics and Data Science, University of Pennsylvania（统计与数据科学系，宾夕法尼亚大学） 纠错

专题命中 Agent评测 ：agent(abstract)；分类 cs.LG

Confusion is the Final Barrier: Rethinking Jailbreak Evaluation and Investigating the Real Misuse Threat of LLMs

Yu Yan, Sheng Sun, Zhe Wang, Yijun Lin, Zenghao Duan, zhifei zheng, Min Liu, Zhiyi yin, Jianping Zhang

机构 * State Key Lab of Processors, Institute of Computing Technology, CAS（中国科学院计算技术研究所状态关键实验室） ； University of Chinese Academy of Sciences（中国科学院大学） ； People’s Public Security University of China（中国人民公安大学） ； Chinese University of Hong Kong（香港大学） 纠错

专题命中 Agent评测 ：planning(abstract)；分类 cs.AI

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem

Hao Song, Yiming Shen, Wenxuan Luo, Leixin Guo, Ting Chen, Jiashui Wang, Beibei Li, Xiaosong Zhang, Jiachi Chen

专题命中 Agent评测 ：agent(abstract)；分类 cs.SE

TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation

Hangyu Li, Qin Zhao, Haoran Xu, Xinyu Jiang, Qingwei Ben, Feiyu Jia, Haoyu Zhao, Liang Xu, Jia Zeng, Hanqing Wang, Bo Dai, Junting Dong, Jiangmiao Pang

机构 * Shanghai AI Laboratory（上海人工智能实验室） ； Zhejiang University（浙江大学） ； The Chinese University of Hong Kong（香港中文大学） ； The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）） ； The University of Hong Kong（香港大学） ； Feeling AI（FeelAI） ； Tsinghua Shenzhen International Graduate School（清华大学深圳国际研究生院） 纠错

专题命中 Agent评测 ：tool use(abstract)；分类 cs.AI

Comments Project page:https://gorgeous2002.github.io/TeleOpBench/, Codes:https://github.com/cyjdlhy/TeleOpBench

Embodied Visuomotor Representation

Levi Burner, Cornelia Fermüller, Yiannis Aloimonos

机构 * Department of Electrical and Computer Engineering, University of Maryland, College Park（电气与计算机工程系，马里兰大学，College Park） ； Institute for Advanced Computer Studies, University of Maryland, College Park（高级计算机研究机构，马里兰大学，College Park） ； Department of Computer Science, University of Maryland, College Park（计算机科学系，马里兰大学，College Park） 纠错

专题命中 Agent评测 ：agent(abstract)

Comments 61 pages, 12 figures, 3 tables

Journal ref npj Robot 3, 30 (2025)

Controlled growth of polar altermagnets via chemical vapor transport

Hiraka Haruhiro, Raktim Datta, Poonam Yadav, Anzar Ali, Suheon Lee, Matthias J. Gutmann, Duhee Yoon, Dirk Wulferding, Xianghan Xu, Moon-Ho Jo, Sang-Wook Cheong, Sungkyun Choi

专题命中 Agent评测 ：agent(abstract)

Comments 12 pages, 8 figures, 1 Table

Journal ref Cryst. Growth Des. 25, 4991 (2025)

Quantifying topological features and irregularities in zebrafish patterns using the sweeping-plane filtration

Nour Khoudari, John Nardini, Alexandria Volkening

专题命中 Agent评测 ：agent(abstract)

Comments 40 pages, 17 figures

Binomial maps: stochastically evolving iterated integer maps for finite populations

Snehal M. Shekatkar

专题命中 Agent评测 ：agent(abstract)

Comments 6 pages, 4 figures

Closed curve covering and multiagent TSP ratios

Travis Dillon, Adrian Dumitrescu

专题命中 Agent评测 ：agent(abstract)

Comments 8 pages, 3 figures

Virucidal Efficacy of Laser-Generated Copper Nanoparticle Coatings Against Model Coronavirus and Herpesvirus

Shahd Bakhet, Rasa Mardosaitė, Mohamed Ahmed Baba, Asta Tamulevičienė, Brigita Abakevičienė, Tomas Klinavičius, Kristupas Dagilis, Simas Račkauskas, Sigitas Tamulevičius, Raimundas Lelešius, Dainius Zienius, Algirdas Šalomskas, Tomas Tamulevičius

专题命中 Agent评测 ：agent(abstract)

Comments 23 pages, 4 figures, 2 tables, 3 supplementary figures, 6 supplementary tables, 4 highlights, 1 graphical abstract

Journal ref ACS Appl. Mater. Interfaces (2025)