AI Agent - arXivDaily 专题

2509.19199 2025-09-30 cs.CL 85%

Agentic Reinforcement Learning with Implicit Step Rewards

Xiaoqian Liu, Ke Wang, Yuchuan Wu, Fei Huang, Yongbin Li, Junge Zhang, Jianbin Jiao

机构 * University of Chinese Academy of Sciences（中国科学院大学）； Tongyi Lab（通义实验室）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）

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

Comments 18 pages, 8 figures

2509.06775 2025-09-30 eess.SY cs.AI cs.IT cs.LG cs.NI cs.SY math.IT 84%

Agentic DDQN-Based Scheduling for Licensed and Unlicensed Band Allocation in Sidelink Networks

Po-Heng Chou, Pin-Qi Fu, Walid Saad, Li-Chun Wang

机构 * Department of Electronics and Electrical Engineering（电子与电气工程系）； Institute of Communications Engineering（通讯工程研究所）； National Yang Ming Chiao Tung University（阳明交通大学）； Research Center for Information Technology Innovation（信息技术创新研究中心）； Academia Sinica（台湾“中央研究院”）； Bradley Department of Electrical and Computer Engineering（电气与计算机工程系）

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

Comments 6 pages, 3 figures, accepted by 2025 IEEE Globecom Workshops

2506.01813 2025-09-30 cs.AI 83%

The Ultimate Test of Superintelligent AI Agents: Can an AI Balance Care and Control in Asymmetric Relationships?

Djallel Bouneffouf, Matthew Riemer, Kush Varshney

机构 * IBM Research（IBM研究院）

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

2509.23270 2025-09-30 cs.AI 83%

Socio-Economic Model of AI Agents

Yuxinyue Qian, Jun Liu

机构 * Beijing University of Posts and Telecommunications（北京邮电大学）

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

2509.24651 2025-09-30 cs.AI 81%

"Stop replacing salt with sugar!'': Towards Intuitive Human-Agent Teaching

Nikolaos Kondylidis, Andrea Rafanelli, Ilaria Tiddi, Annette ten Teije, Frank van Harmelen

机构 * Vrije Universiteit Amsterdam（荷兰阿姆斯特丹自由大学）； University of Pisa（比萨大学）

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

Comments 22nd European Conference on Multi-Agent Systems (EUMAS 2025)

2509.23655 2025-09-30 cs.RO cs.AI cs.CV cs.LG 81%

Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models

Rokas Bendikas, Daniel Dijkman, Markus Peschl, Sanjay Haresh, Pietro Mazzaglia

机构 * Centre for Artificial Intelligence, UCL（人工智能中心，伦敦大学学院）； Qualcomm AI Research（高通人工智能研究）

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

Comments Presented at 9th Conference on Robot Learning (CoRL 2025), Seoul, Korea

2509.23006 2025-09-30 cs.AI 79%

Creative Adversarial Testing (CAT): A Novel Framework for Evaluating Goal-Oriented Agentic AI Systems

Hassen Dhrif

机构 * Amazon（亚马逊）

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

2509.24698 2025-09-30 cs.CR 78%

LISA Technical Report: An Agentic Framework for Smart Contract Auditing

Izaiah Sun, Daniel Tan, Andy Deng

专题命中 Agent评测：agentic(title,abstract)

Comments A technical report with 10 pages

2509.24995 2025-09-30 cs.RO cs.SY eess.SY 75%

Path Diffuser: Diffusion Model for Data-Driven Traffic Simulator

Da Saem Lee, Akash Karthikeyan, Yash Vardhan Pant, Sebastian Fischmeister

机构 * Department of Electrical and Computer Engineering, University of Waterloo（电气与计算机工程系，滑铁卢大学）

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

2509.24002 2025-09-30 cs.CL cs.AI 73%

MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

Zijian Wu, Xiangyan Liu, Xinyuan Zhang, Lingjun Chen, Fanqing Meng, Lingxiao Du, Yiran Zhao, Fanshi Zhang, Yaoqi Ye, Jiawei Wang, Zirui Wang, Jinjie Ni, Yufan Yang, Arvin Xu, Michael Qizhe Shieh

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

Comments 42 pages, 27 figures, 10 tables

2505.10482 2025-09-30 cs.LG cs.AI 73%

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps

Ningyuan Yang, Jiaxuan Gao, Feng Gao, Yi Wu, Chao Yu

机构 * Tsinghua University（清华大学）

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

Comments 9 pages for main text, 23 pages in total, submitted to Neurips, 13 figures

2509.24127 2025-09-30 cs.AI cs.DB 70%

Transparent, Evaluable, and Accessible Data Agents: A Proof-of-Concept Framework

Nooshin Bahador

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

Comments 20 pages, 11 figures

2509.22735 2025-09-30 cs.CY cs.AI 70%

Regulating the Agency of LLM-based Agents

Seán Boddy, Joshua Joseph

机构 * Berkman Klein Center for Internet & Society（互联网与社会伯克曼克莱因中心）； Harvard University（哈佛大学）

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

Comments 4 pages

2509.24923 2025-09-30 cs.LG cs.AI cs.CL 67%

When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training

Sanxing Chen, Xiaoyin Chen, Yukun Huang, Roy Xie, Bhuwan Dhingra

机构 * Duke University（杜克大学）； Mila - Québec AI Institute（魁北克AI研究所）； Université de Montréal（蒙特利尔大学）

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

2509.24927 2025-09-30 cs.AI cs.RO cs.SE 62%

When Autonomous Vehicle Meets V2X Cooperative Perception: How Far Are We?

An Guo, Shuoxiao Zhang, Enyi Tang, Xinyu Gao, Haomin Pang, Haoxiang Tian, Yanzhou Mu, Wu Wen, Chunrong Fang, Zhenyu Chen

机构 * Guangzhou University（广州大学）； Nanyang Technological University（南洋理工大学）； Shenzhen Research Institute of Nanjing University（南京大学深圳研究院）

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

Comments The paper has been accepted by the 40th IEEE/ACM International Conference on Automated Software Engineering, ASE 2025

Journal ref Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering.2025

2509.24527 2025-09-30 cs.AI cs.LG cs.RO stat.ML 62%

Training Agents Inside of Scalable World Models

Danijar Hafner, Wilson Yan, Timothy Lillicrap

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

Comments Website: https://danijar.com/dreamer4/

2509.24389 2025-09-30 cs.CL cs.AI 62%

LLaDA-MoE: A Sparse MoE Diffusion Language Model

Fengqi Zhu, Zebin You, Yipeng Xing, Zenan Huang, Lin Liu, Yihong Zhuang, Guoshan Lu, Kangyu Wang, Xudong Wang, Lanning Wei, Hongrui Guo, Jiaqi Hu, Wentao Ye, Tieyuan Chen, Chenchen Li, Chengfu Tang, Haibo Feng, Jun Hu, Jun Zhou, Xiaolu Zhang, Zhenzhong Lan, Junbo Zhao, Da Zheng, Chongxuan Li, Jianguo Li, Ji-Rong Wen

机构 * Renmin University of China（中国人民大学）； Ant Group（蚂蚁集团）； Shanghai Jiao Tong University（上海交通大学）； Zhejiang University（浙江大学）

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

2509.23992 2025-09-30 cs.LG cs.AI 62%

Guide: Generalized-Prior and Data Encoders for DAG Estimation

Amartya Roy, Devharish N, Shreya Ganguly, Kripabandhu Ghosh

机构 * SIRE, Indian Institute of Technology Delhi（印度理工学院德里学院）； Robert Bosch GmbH（罗伯特·博世有限公司）； Indian Institute of Science Education and Research, Kolkata（印度科学教育与研究学院，科拉卡特）

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

2509.13341 2025-09-30 cs.AI cs.LG 62%

Imagined Autocurricula

Ahmet H. Güzel, Matthew Thomas Jackson, Jarek Luca Liesen, Tim Rocktäschel, Jakob Nicolaus Foerster, Ilija Bogunovic, Jack Parker-Holder

机构 * University College London AI Centre（伦敦大学学院人工智能中心）； University of Oxford（牛津大学）

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

2509.22704 2025-09-30 cs.DC cs.AI cs.SE 62%

Intelligent Load Balancing in Cloud Computer Systems

Leszek Sliwko

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

Comments A thesis submitted in partial fulfilment of the requirements of the University of Westminster for the degree of Doctor of Philosophy

2506.10171 2025-09-30 cs.CR cs.AI cs.CL 62%

Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents

Saswat Das, Jameson Sandler, Ferdinando Fioretto

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

2509.22814 2025-09-30 cs.CR 60%

Model Context Protocol for Vision Systems: Audit, Security, and Protocol Extensions

Aditi Tiwari, Akshit Bhalla, Darshan Prasad

专题命中 Agent评测：agent(abstract,comments)；planning(comments)

Comments Accepted to NeurIPS 2025 Workshop on Bridging Language, Agent, and World Models for Reasoning and Planning (LAW 2025)

2509.23244 2025-09-30 cs.RO cs.AI 57%

Online Dynamic Goal Recognition in Gym Environments

Shamir Matan, Elhadad Osher, Nageris Ben, Mirsky Reuth

机构 * Bar-Ilan University（巴伊兰大学）； Tufts University（塔夫茨大学）

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2509.21143 2025-09-30 cs.RO cs.CL 57%

Automotive-ENV: Benchmarking Multimodal Agents in Vehicle Interface Systems

Junfeng Yan, Biao Wu, Meng Fang, Ling Chen

机构 * Australian Artificial Intelligence Institute（澳大利亚人工智能研究所）； University of Liverpool（利物浦大学）

专题命中 Agent评测：agent(abstract)；分类 cs.CL

Comments 10 pages, 5 figures,

2505.21979 2025-09-30 cs.CL 57%

Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset

Fakhraddin Alwajih, Samar M. Magdy, Abdellah El Mekki, Omer Nacar, Youssef Nafea, Safaa Taher Abdelfadil, Abdulfattah Mohammed Yahya, Hamzah Luqman, Nada Almarwani, Samah Aloufi, Baraah Qawasmen, Houdaifa Atou, Serry Sibaee, Hamzah A. Alsayadi, Walid Al-Dhabyani, Maged S. Al-shaibani, Aya El Aatar, Nour Qandos, Rahaf Alhamouri, Samar Ahmad, Mohammed Anwar Al-Ghrawi, Aminetou Yacoub, Ruwa AbuHweidi, Vatimetou Mohamed Lemin, Reem Abdel-Salam, Ahlam Bashiti, Aisha Alansari, Ahmed Ashraf, Nora Alturayeif, Alcides Alcoba Inciarte, Adel Ammar, Abdelrahim A. Elmadany, Mohamedou Cheikh Tourad, Ismail Berrada, Mustafa Jarrar, Shady Shehata, Muhammad Abdul-Mageed

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

Comments https://github.com/UBC-NLP/pearl

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

2509.24194 2025-09-30 cs.CV 50%

An Efficient 3D Latent Diffusion Model for T1-contrast Enhanced MRI Generation

Zach Eidex, Mojtaba Safari, Jie Ding, Richard Qiu, Justin Roper, David Yu, Hui-Kuo Shu, Zhen Tian, Hui Mao, Xiaofeng Yang

专题命中 Agent评测：agent(abstract)

2506.15635 2025-09-30 cs.CV cs.RO 50%

FindingDory: A Benchmark to Evaluate Memory in Embodied Agents

Karmesh Yadav, Yusuf Ali, Gunshi Gupta, Yarin Gal, Zsolt Kira

机构 * Georgia Tech（佐治亚理工学院）； University of Oxford（牛津大学）

专题命中 Agent评测：planning(abstract)

Comments Our dataset and code can be found at: https://findingdory-benchmark.github.io/

2412.19995 2025-09-30 cs.NI 50%

Scalability Assurance in SFC provisioning via Distributed Design for Deep Reinforcement Learning

Murat Arda Onsu, Poonam Lohan, Burak Kantarci, Emil Janulewicz

专题命中 Agent评测：agent(abstract)

Comments 6 pages, 5 figures, under submission to IEEE International Conference on Communications (ICC 2025)

1. Agent评测 29 篇

Agentic Reinforcement Learning with Implicit Step Rewards

Agentic DDQN-Based Scheduling for Licensed and Unlicensed Band Allocation in Sidelink Networks

The Ultimate Test of Superintelligent AI Agents: Can an AI Balance Care and Control in Asymmetric Relationships?

Socio-Economic Model of AI Agents

"Stop replacing salt with sugar!'': Towards Intuitive Human-Agent Teaching

Focusing on What Matters: Object-Agent-centric Tokenization for Vision Language Action models

Creative Adversarial Testing (CAT): A Novel Framework for Evaluating Goal-Oriented Agentic AI Systems

LISA Technical Report: An Agentic Framework for Smart Contract Auditing

Path Diffuser: Diffusion Model for Data-Driven Traffic Simulator

MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps

Transparent, Evaluable, and Accessible Data Agents: A Proof-of-Concept Framework

Regulating the Agency of LLM-based Agents

When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training

When Autonomous Vehicle Meets V2X Cooperative Perception: How Far Are We?

Training Agents Inside of Scalable World Models

LLaDA-MoE: A Sparse MoE Diffusion Language Model

Guide: Generalized-Prior and Data Encoders for DAG Estimation

Imagined Autocurricula

Intelligent Load Balancing in Cloud Computer Systems

Beyond Jailbreaking: Auditing Contextual Privacy in LLM Agents

Model Context Protocol for Vision Systems: Audit, Security, and Protocol Extensions

Online Dynamic Goal Recognition in Gym Environments

Automotive-ENV: Benchmarking Multimodal Agents in Vehicle Interface Systems

Pearl: A Multimodal Culturally-Aware Arabic Instruction Dataset

Is Thompson Sampling Susceptible to Algorithmic Collusion?

An Efficient 3D Latent Diffusion Model for T1-contrast Enhanced MRI Generation

FindingDory: A Benchmark to Evaluate Memory in Embodied Agents

Scalability Assurance in SFC provisioning via Distributed Design for Deep Reinforcement Learning