AI Agent

Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Tasks

Ruofan Lu, Yichen Li, Yintong Huo

机构 * Singapore Management University（新加坡国立管理大学） 纠错

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

Comments Accepted by ASE 2025 NIER

N-Agent Ad Hoc Teamwork

Caroline Wang, Arrasy Rahman, Ishan Durugkar, Elad Liebman, Peter Stone

机构 * Sony AI（索尼人工智能） 纠错

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

Journal ref Proceedings of the 38th International Conference on Neural Information Processing Systems (NIPS '24), Vol. 37 (2024), Article 3551, 111832-111862

Reliability, Embeddedness, and Agency: A Utility-Driven Mathematical Framework for Agent-Centric AI Adoption

Faruk Alpay, Taylan Alpay

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

Comments 17 pages, 7 figures, 4 tables

Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework

Zheye Deng, Chunkit Chan, Tianshi Zheng, Wei Fan, Weiqi Wang, Yangqiu Song

机构 * Department of Computer Science and Engineering, HKUST, Hong Kong SAR, China（计算机科学与工程系，香港科技大学，香港特别行政区，中国） 纠错

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

Comments Under Review

GALA: Can Graph-Augmented Large Language Model Agentic Workflows Elevate Root Cause Analysis?

Yifang Tian, Yaming Liu, Zichun Chong, Zihang Huang, Hans-Arno Jacobsen

机构 * University of Toronto（多伦多大学） 纠错

专题命中 Agent评测 ：agentic(title)；分类 cs.AI

Comments 12 pages, 5 figures

TeleAntiFraud-28k: An Audio-Text Slow-Thinking Dataset for Telecom Fraud Detection

Zhiming Ma, Peidong Wang, Minhua Huang, Jingpeng Wang, Kai Wu, Xiangzhao Lv, Yachun Pang, Yin Yang, Wenjie Tang, Yuchen Kang

机构 * China Mobile Internet Company Ltd.（中国移动互联网有限公司） ； Northeastern University（东北大学） 纠错

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

Learning Zero-Sum Linear Quadratic Games with Improved Sample Complexity and Last-Iterate Convergence

Jiduan Wu, Anas Barakat, Ilyas Fatkhullin, Niao He

机构 * Department of Computer Science, ETH Zürich（计算机科学系，苏黎世联邦理工学院） 纠错

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

ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering

Kaisi Guan, Zhengfeng Lai, Yuchong Sun, Peng Zhang, Wei Liu, Kieran Liu, Meng Cao, Ruihua Song

机构 * Renmin University of China（中国人民大学） ； Apple（苹果公司） 纠错

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

Comments International Conference on Computer Vision 2025

A Multi-Resolution Benchmark Framework for Spatial Reasoning Assessment in Neural Networks

Manuela Imbriani, Gina Belmonte, Mieke Massink, Alessandro Tofani, Vincenzo Ciancia

机构 * Dipartimento di Fisica, Università di Pisa（普拉蒂亚大学物理系） ； Istituto di Scienza e Tecnologie dell’Informazione "A.Faedo", CNR（信息科学与技术研究所（A.Faedo）） ； Azienda Toscana Nord Ovest, S.C.Fisica Sanitaria Nord（托斯卡纳北西医疗公司，北西医学物理分公司） 纠错

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

Game Reasoning Arena: A Framework and Benchmark for Assessing Reasoning Capabilities of Large Language Models via Game Play

Lucia Cipolina-Kun, Marianna Nezhurina, Jenia Jitsev

机构 * LAION Juelich Supercomputing Center (JSC)（LAION尤利奇超级计算机中心（JSC）） ； Research Center Juelich (FZJ)（尤利奇研究中心（FZJ）） 纠错

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

Seldonian Reinforcement Learning for Ad Hoc Teamwork

Edoardo Zorzi, Alberto Castellini, Leonidas Bakopoulos, Georgios Chalkiadakis, Alessandro Farinelli

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

Comments Presented at the 2nd Reinforcement Learning Conference (RLC2025), Edmonton, Canada. To be published in the Proceedings of the Reinforcement Learning Journal 2025

Model-free reinforcement learning with noisy actions for automated experimental control in optics

Lea Richtmann, Viktoria-S. Schmiesing, Dennis Wilken, Jan Heine, Aaron Tranter, Avishek Anand, Tobias J. Osborne, Michèle Heurs

机构 * Institute for Gravitational Physics（引力物理研究所） ； Leibniz University Hannover（汉诺威莱布尼茨大学） ； Institute for Theoretical Physics（理论物理研究所） ； Institute of Photonics（光子研究所） ； Quantum Science and Technology（量子科学与技术） ； Australian National University（澳大利亚国立大学） ； Software Technology Department（软件技术系） ； Delft University of Technology（代尔夫特理工大学） 纠错

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

Comments 10 pages + 12 pages appendices, 2 + 12 figures

SimInterview: Transforming Business Education through Large Language Model-Based Simulated Multilingual Interview Training System

Truong Thanh Hung Nguyen, Tran Diem Quynh Nguyen, Hoang Loc Cao, Thi Cam Thanh Tran, Thi Cam Mai Truong, Hung Cao

机构 * Analytics Everywhere Lab, University of New Brunswick, Canada（新不伦瑞克大学分析 everywhere 实验室） ； University of Foreign Language Studies, University of Danang, Vietnam（越南丹绒大学外语学院） ； Faculty of Information Technology, University of Science, VNU-HCM, Vietnam（越南胡志明市大学信息科技学院） ； Faculty of Economics and Accounting, Quy Nhon University, Vietnam（越南奎隆大学经济与会计学院） ； Faculty of Natural Sciences, Quy Nhon University, Vietnam（越南奎隆大学自然科学学院） 纠错

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

Comments Published as a conference paper at ICEFM 2025

A Multi-Task Evaluation of LLMs' Processing of Academic Text Input

Tianyi Li, Yu Qin, Olivia R. Liu Sheng

机构 * Department of Decisions, Operations and Technology, CUHK（决策、运营与技术系，香港中文大学） ； Department of Information Systems, Arizona State University（信息系统系，亚利桑那州立大学） 纠错

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

Precise Action-to-Video Generation Through Visual Action Prompts

Yuang Wang, Chao Wen, Haoyu Guo, Sida Peng, Minghan Qin, Hujun Bao, Xiaowei Zhou, Ruizhen Hu

机构 * Xiangjiang Lab（湘江实验室） ； Zhejiang University（浙江大学） ； Fudan University（复旦大学） ； Tsinghua University（清华大学） ； Shenzhen University（深圳大学） 纠错

专题命中 Agent评测 ：agent(abstract)

Comments Accepted to ICCV 2025. Project page: https://zju3dv.github.io/VAP/

When motivation can be more than a message: designing agents to boost physical activity

Alessandro Silacci, Maurizio Caon, Mauro Cherubini

专题命中 Agent评测 ：agent(abstract)

Comments This is a pre-peer-review version of a paper with the same title accepted at 20th IFIP TC13 International Conference on Human-Computer Interaction (INTERACT 2025)

Embodied Image Quality Assessment for Robotic Intelligence

Jianbo Zhang, Chunyi Li, Jie Hao, Jun Jia, Huiyu Duan, Guoquan Zheng, Liang Yuan, Guangtao Zhai

机构 * Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University（图像通信与网络工程研究所，上海交通大学） ； College of Information Science and Technology, Beijing University of Chemical Technology（信息科学与技术学院，北京化工大学） ； USC-SJTU Institute of Cultural and Creative Industry, Shanghai Jiao Tong University（USC-SJTU文化产业与创意产业研究所，上海交通大学） 纠错

专题命中 Agent评测 ：agent(abstract)

Behavioral and Symbolic Fillers as Delay Mitigation for Embodied Conversational Agents in Virtual Reality

Denmar Mojan Gonzales, Snehanjali Kalamkar, Sophie Jörg, Jens Grubert

专题命中 Agent评测 ：agent(abstract)

Comments Accepted to IEEE Transactions on Visualization and Computer Graphics