AI Agent - arXivDaily 专题

2405.17463 2025-09-30 cs.GT cs.LG 57%

Is Thompson Sampling Susceptible to Algorithmic Collusion?

Yi Xiong, Ningyuan Chen, Xuefeng Gao

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2509.21978 2025-09-29 cs.CL 57%

MotivGraph-SoIQ: Integrating Motivational Knowledge Graphs and Socratic Dialogue for Enhanced LLM Ideation

Xinping Lei, Tong Zhou, Yubo Chen, Kang Liu, Jun Zhao

机构 * The Key Laboratory of Cognition and Decision Intelligence for Complex Systems（认知与决策智能复杂系统重点实验室）； School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）； Hunan Provincial Key Laboratory of Philosophy and Social Sciences of Artificial Intelligence and Precision International, Hunan Normal University（湖南省人工智能与精准哲学社会科学省级重点实验室，湖南师范大学）； Beijing University of Posts and Telecommunications（北京邮电大学）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments EMNLP2025 Findings

2506.02863 2025-09-29 eess.AS cs.AI cs.SD 57%

CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech

Helin Wang, Jiarui Hai, Dading Chong, Karan Thakkar, Tiantian Feng, Dongchao Yang, Junhyeok Lee, Thomas Thebaud, Laureano Moro Velazquez, Jesus Villalba, Zengyi Qin, Shrikanth Narayanan, Mounya Elhiali, Najim Dehak

机构 * Johns Hopkins University（约翰霍普金斯大学）； Peking University（北京大学）； Chinese University of Hong Kong（香港中文大学）； University of Southern California（南加州大学）； Massachusetts Institute of Technology（麻省理工学院）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2509.21234 2025-09-26 cs.LG cs.MA 57%

AbideGym: Turning Static RL Worlds into Adaptive Challenges

Abi Aryan, Zac Liu, Aaron Childress

机构 * Abide AI

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2509.21188 2025-09-26 cs.HC cs.AI cs.CY cs.IR 57%

Adoption, usability and perceived clinical value of a UK AI clinical reference platform (iatroX): a mixed-methods formative evaluation of real-world usage and a 1,223-respondent user survey

Kolawole Tytler

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

2404.02688 2025-09-26 cs.LG math.CT 57%

Reinforcement Learning in Categorical Cybernetics

Jules Hedges, Riu Rodríguez Sakamoto

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments In Proceedings ACT 2024, arXiv:2509.18357

Journal ref EPTCS 429, 2025, pp. 270-286

2509.19411 2025-09-25 cs.NI cs.HC cs.LG 57%

Poster: ChatIYP: Enabling Natural Language Access to the Internet Yellow Pages Database

Vasilis Andritsoudis, Pavlos Sermpezis, Ilias Dimitriadis, Athena Vakali

机构 * Aristotle University of Thessaloniki Thessaloniki Greece ； Measurement Lab\ for Science \& Society Portland OR United States ； Aristotle University of Thessaloniki ； Measurement Lab\ for Science \& Society

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

Comments ACM Internet Measurement Conference (IMC) 2025

2509.19234 2025-09-24 cs.LG eess.SP 57%

Stability and Generalization of Adversarial Diffusion Training

Hesam Hosseini, Ying Cao, Ali H. Sayed

机构 * School of Engineering, École Polytechnique Fédérale de Lausanne（瑞士联邦理工学院工程学院）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2508.02159 2025-09-24 cs.LG 57%

PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning

Dongchi Huang, Jiaqi Wang, Yang Li, Chunhe Xia, Tianle Zhang, Kaige Zhang

机构 * School of Computer Science, University of Beihang, Beijing, China（北京航空航天大学计算机学院）； School of Computer Science, Chinese University of Hong Kong, Hongkong, China（香港中文大学计算机学院）； JD Explore Academy, Beijing, China（京东探索研究院）； North Automatic Control Institute, Taiyuan, China（太原北自动控制研究所）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments ICML 2025

2509.18632 2025-09-24 cs.CL 57%

A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users

Nishant Balepur, Matthew Shu, Yoo Yeon Sung, Seraphina Goldfarb-Tarrant, Shi Feng, Fumeng Yang, Rachel Rudinger, Jordan Lee Boyd-Graber

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments EMNLP 2025

2509.18626 2025-09-24 cs.RO cs.AI 57%

The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving

Jay Patrikar, Apoorva Sharma, Sushant Veer, Boyi Li, Sebastian Scherer, Marco Pavone

机构 * Field AI ； NVIDIA ； Carnegie Mellon University（卡内基梅隆大学）； Stanford University（斯坦福大学）

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

Comments 8 pages, 5 figures

2509.18175 2025-09-24 cs.CL 57%

ERFC: Happy Customers with Emotion Recognition and Forecasting in Conversation in Call Centers

Aditi Debsharma, Bhushan Jagyasi, Surajit Sen, Priyanka Pandey, Devicharith Dovari, Yuvaraj V. C, Rosalin Parida, Gopali Contractor

机构 * Center for Advanced AI, Accenture（Accenture高级人工智能中心）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments 7 pages, 6 Figures, 4 Tables, 18 References

2509.17728 2025-09-23 cs.LG cs.MA 57%

A non-smooth regularization framework for learning over multitask graphs

Yara Zgheib, Luca Calatroni, Marc Antonini, Roula Nassif

机构 * Université Côte d’Azur, I3S Laboratory, CNRS, France（法国大学皮特里特大学I3S实验室，CNRS）； Machine Learning Genoa Center (MaLGa), Department of Computer Science, University of Genoa（热那亚大学计算机科学系机器学习中心（MaLGa））

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2509.17092 2025-09-23 cs.LG 57%

On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark

Michelangelo Conserva, Remo Sasso, Paulo Rauber

机构 * School of Electronic Engineering and Computer Science（电子工程与计算机科学学院）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2504.09407 2025-09-22 cs.CL cs.HC 57%

UXAgent: A System for Simulating Usability Testing of Web Design with LLM Agents

Yuxuan Lu, Bingsheng Yao, Hansu Gu, Jing Huang, Jessie Wang, Yang Li, Jiri Gesi, Qi He, Toby Jia-Jun Li, Dakuo Wang

机构 * Northeastern University（东北大学）； Amazon（亚马逊）； University of Notre Dame（诺特尔大学）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

2509.15076 2025-09-19 cs.LG cs.CV 57%

Forecasting and Visualizing Air Quality from Sky Images with Vision-Language Models

Mohammad Saleh Vahdatpour, Maryam Eyvazi, Yanqing Zhang

机构 * Georgia State University（佐治亚州立大学）； Savannah College of Art and Design（萨凡纳艺术与设计学院）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Published at ICCVW 2025

2509.13869 2025-09-18 cs.CL 57%

Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs

Yang Liu, Chenhui Chu

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments 38 pages, 31 figures

2506.08375 2025-09-17 cs.CL 57%

EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models

Tao Zou, Xinghua Zhang, Haiyang Yu, Minzheng Wang, Fei Huang, Yongbin Li

机构 * Tongyi Lab, Alibaba Group（通义实验室，阿里巴巴集团）

专题命中 Agent评测：workflow(abstract)；分类 cs.CL

Comments Accepted by EMNLP 2025

2309.07510 2025-09-17 cs.RO cs.AI cs.CV 57%

Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions

Ruihai Wu, Kai Cheng, Yan Shen, Chuanruo Ning, Guanqi Zhan, Hao Dong

机构 * CFCS, School of CS, PKU（计算机学院，北京大学）； School of EECS, PKU（电子工程系，北京大学）； University of Oxford（牛津大学）； National Key Laboratory for Multimedia Information Processing, School of CS, PKU（多媒体信息处理国家重点实验室，计算机学院，北京大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments In 37th Conference on Neural Information Processing Systems (NeurIPS 2023). Website at https://chengkaiacademycity.github.io/EnvAwareAfford/

2505.09315 2025-09-17 cs.RO cs.CV cs.LG 57%

TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving

Xuefeng Jiang, Yuan Ma, Pengxiang Li, Leimeng Xu, Xin Wen, Kun Zhan, Zhongpu Xia, Peng Jia, Xianpeng Lang, Sheng Sun

机构 * LiAuto Inc（LiAuto公司）； Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）； School of Vehicle and Mobility, Tsinghua University（清华大学车辆与移动研究所）

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

Comments Under review

2509.11357 2025-09-16 cs.LG cs.GT 57%

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）

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2508.16347 2025-09-16 cs.CR cs.AI 57%

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）

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

2506.02040 2025-09-16 cs.CR cs.SE 57%

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

2505.12748 2025-09-16 cs.RO cs.AI cs.CV 57%

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）

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

2502.13818 2025-09-15 cs.CV cs.LG 57%

Building Age Estimation: A New Multi-Modal Benchmark Dataset and Community Challenge

Nikolaos Dionelis, Alessandra Feliciotti, Mattia Marconcini, Devis Peressutti, Nika Oman Kadunc, JaeWan Park, Hagai Raja Sinulingga, Steve Andreas Immanuel, Ba Tran, Caroline Arnold, Nicolas Longépé

机构 * European Space Agency（欧洲航天局）； Φ \Phi -lab（Phi实验室）； ESRIN（ESRIN研究所）； MindEarth（MindEarth公司）； Sinergise/ Planet（Sinergise/Planet公司）； TelePIX（TelePIX公司）； Axelspace Corporation（Axelspace公司）； Helmholtz Institute Hereon（海德堡研究所）； German Climate Computing Center DKRZ（德国气候计算中心DKRZ）

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

Comments 16 pages, 20 figures, 1 table, Submitted

2509.07009 2025-09-11 q-bio.NC cs.AI cs.SY eess.SY 57%

Computational Concept of the Psyche (in Russian)

Anton Kolonin, Vladimir Kryukov

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 14 pages, in Russian, 2 figures, submitted to Neuroinformatics-2025 conference

2407.13729 2025-09-11 cs.CL 57%

Baba Is AI: Break the Rules to Beat the Benchmark

Nathan Cloos, Meagan Jens, Michelangelo Naim, Yen-Ling Kuo, Ignacio Cases, Andrei Barbu, Christopher J. Cueva

机构 * MIT（麻省理工学院）； Department of Computer Science, University of Virginia, USA（弗吉尼亚大学计算机科学系）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments 8 pages, 8 figures

2509.07994 2025-09-11 eess.IV cs.CV cs.LG 57%

STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery

David Robinson, Animesh Gupta, Rizwan Quershi, Qiushi Fu, Mubarak Shah

机构 * Center for Research in Computer Vision, University of Central Florida（计算机视觉研究中心，佛罗里达中央大学）； Mechanical and Aerospace Engineering, University of Central Florida（机械与航空航天工程，佛罗里达中央大学）

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

Comments 6 pages

2509.07614 2025-09-10 quant-ph cs.AI 57%

From Classical Data to Quantum Advantage -- Quantum Policy Evaluation on Quantum Hardware

Daniel Hein, Simon Wiedemann, Markus Baumann, Patrik Felbinger, Justin Klein, Maximilian Schieder, Jonas Stein, Daniëlle Schuman, Thomas Cope, Steffen Udluft

机构 * Siemens AG（西门子股份公司）； Technical University of Munich（慕尼黑技术大学）； LMU Munich（慕尼黑大学）； IQM Germany（德国IQM）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2509.07193 2025-09-10 eess.IV cs.AI cs.CV 57%

Evaluation of Machine Learning Reconstruction Techniques for Accelerated Brain MRI Scans

Jonathan I. Mandel, Shivaprakash Hiremath, Hedyeh Keshtgar, Timothy Scholl, Sadegh Raeisi

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

Comments This work has been submitted to Radiology: Artificial Intelligence for possible publication

1. Agent评测 15866 篇

Is Thompson Sampling Susceptible to Algorithmic Collusion?

MotivGraph-SoIQ: Integrating Motivational Knowledge Graphs and Socratic Dialogue for Enhanced LLM Ideation

CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech

AbideGym: Turning Static RL Worlds into Adaptive Challenges

Adoption, usability and perceived clinical value of a UK AI clinical reference platform (iatroX): a mixed-methods formative evaluation of real-world usage and a 1,223-respondent user survey

Reinforcement Learning in Categorical Cybernetics

Poster: ChatIYP: Enabling Natural Language Access to the Internet Yellow Pages Database

Stability and Generalization of Adversarial Diffusion Training

PIGDreamer: Privileged Information Guided World Models for Safe Partially Observable Reinforcement Learning

A Good Plan is Hard to Find: Aligning Models with Preferences is Misaligned with What Helps Users

The Case for Negative Data: From Crash Reports to Counterfactuals for Reasonable Driving

ERFC: Happy Customers with Emotion Recognition and Forecasting in Conversation in Call Centers

A non-smooth regularization framework for learning over multitask graphs

On the Limits of Tabular Hardness Metrics for Deep RL: A Study with the Pharos Benchmark

UXAgent: A System for Simulating Usability Testing of Web Design with LLM Agents

Forecasting and Visualizing Air Quality from Sky Images with Vision-Language Models

Do LLMs Align Human Values Regarding Social Biases? Judging and Explaining Social Biases with LLMs

EIFBENCH: Extremely Complex Instruction Following Benchmark for Large Language Models

Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions

TransDiffuser: Diverse Trajectory Generation with Decorrelated Multi-modal Representation for End-to-end Autonomous Driving

Online Omniprediction with Long-Term Constraints

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

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

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

Building Age Estimation: A New Multi-Modal Benchmark Dataset and Community Challenge

Computational Concept of the Psyche (in Russian)

Baba Is AI: Break the Rules to Beat the Benchmark

STROKEVISION-BENCH: A Multimodal Video And 2D Pose Benchmark For Tracking Stroke Recovery

From Classical Data to Quantum Advantage -- Quantum Policy Evaluation on Quantum Hardware

Evaluation of Machine Learning Reconstruction Techniques for Accelerated Brain MRI Scans