AI Agent - arXivDaily 专题

2510.13792 2025-10-16 cs.LG cs.AI 62%

Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach

Ziqing Lu, Lifeng Lai, Weiyu Xu

机构 * University of Iowa（爱荷华大学）； University of California, Davis（加州大学戴维斯分校）

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

2510.12835 2025-10-16 cs.CL cs.AI 62%

Repurposing Annotation Guidelines to Instruct LLM Annotators: A Case Study

Kon Woo Kim, Rezarta Islamaj, Jin-Dong Kim, Florian Boudin, Akiko Aizawa

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

Comments 11 pages, 2 figures, 3 tables, This is a preprint of the article accepted at NLDB 2025 (Springer LNCS). The final version is available at https://doi.org/10.1007/978-3-031-97144-0_13

Journal ref In International Conference on Applications of Natural Language to Information Systems, pp. 140-151. Cham: Springer Nature Switzerland, 2025

2507.19842 2025-10-15 cs.SE cs.AI 62%

A Cooperative Approach for Knowledge-based Business Process Design in a Public Authority

Mohammad Azarijafari, Luisa Mich, Michele Missikoff, Oleg Missikoff

机构 * University of Trento（特伦托大学）； National Research Council (CNR)（国家研究 council）； Sapienza University of Rome（罗马大学）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.SE

2510.10475 2025-10-14 cs.CL cs.AI 62%

Assessing Large Language Models for Structured Medical Order Extraction

A H M Rezaul Karim, Ozlem Uzuner

机构 * George Mason University（乔治·马歇尔大学）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

2510.08794 2025-10-13 cs.LG cs.AI 62%

Deceptive Exploration in Multi-armed Bandits

I. Arda Vurankaya, Mustafa O. Karabag, Wesley A. Suttle, Jesse Milzman, David Fridovich-Keil, Ufuk Topcu

机构 * The University of Texas at Austin（德克萨斯大学奥斯汀分校）； The U.S. Army Research Laboratory（美国陆军研究实验室）

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

2504.03955 2025-10-13 cs.LG cs.AI physics.data-an 62%

DeepOHeat-v1: Efficient Operator Learning for Fast and Trustworthy Thermal Simulation and Optimization in 3D-IC Design

Xinling Yu, Ziyue Liu, Hai Li, Yixing Li, Xin Ai, Zhiyu Zeng, Ian Young, Zheng Zhang

机构 * Department of Electrical and Computer Engineering, University of California, Santa Barbara（电气与计算机工程系，加州大学圣巴巴拉分校）； Department of Computer Science, University of California, Santa Barbara（计算机科学系，加州大学圣巴巴拉分校）； Cadence Design Systems（Cadence设计系统）； Intel Corporation（英特尔公司）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

Comments Published by IEEE TCPMT

2506.14787 2025-10-10 cs.LG cs.AI 62%

Topology-Aware and Highly Generalizable Deep Reinforcement Learning for Efficient Retrieval in Multi-Deep Storage Systems

Funing Li, Yuan Tian, Ruben Noortwyck, Jifeng Zhou, Liming Kuang, Robert Schulz

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

2510.02417 2025-10-06 cs.ET cs.AI cs.LG 62%

NEURODNAAI: Neural pipeline approaches for the advancing dna-based information storage as a sustainable digital medium using deep learning framework

Rakesh Thakur, Lavanya Singh, Yashika, Manomay Bundawala, Aruna Kumar

机构 * Amity Centre for Artificial Intelligence, Amity University, India（阿米蒂大学人工智能中心，阿米蒂大学，印度）； Amity School of Engineering and Technology, Amity University, India（阿米蒂工程与技术学院，阿米蒂大学，印度）； Amity Institute of Biotechnology, Amity University, India（阿米蒂生物技术学院，阿米蒂大学，印度）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

2510.01375 2025-10-03 cs.AI cs.CL 62%

Fine-tuning with RAG for Improving LLM Learning of New Skills

Humaid Ibrahim, Nikolai Rozanov, Marek Rei

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.CL

Comments Under review at ICLR 2026

2509.23550 2025-09-30 cs.CL cs.AI 62%

Automatic Speech Recognition for Greek Medical Dictation

Vardis Georgilas, Themos Stafylakis

机构 * Department of Informatics, Athens University of Economics and Business（阿提卡经济与商业大学信息学院）； Omilia Natural Language Solutions Ltd.（Omilia自然语言解决方案有限公司）； Archimedes/Athena RC（阿基米德/雅典RC）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

2508.18244 2025-09-30 cs.LG cs.AI 62%

Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data

Chu-Cheng Lin, Daiyi Peng, Yifeng Lu, Ming Zhang, Eugene Ie

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

2504.03603 2025-09-22 cs.AI cs.LG 62%

Towards deployment-centric multimodal AI beyond vision and language

Xianyuan Liu, Jiayang Zhang, Shuo Zhou, Thijs L. van der Plas, Avish Vijayaraghavan, Anastasiia Grishina, Mengdie Zhuang, Daniel Schofield, Christopher Tomlinson, Yuhan Wang, Ruizhe Li, Louisa van Zeeland, Sina Tabakhi, Cyndie Demeocq, Xiang Li, Arunav Das, Orlando Timmerman, Thomas Baldwin-McDonald, Jinge Wu, Peizhen Bai, Zahraa Al Sahili, Omnia Alwazzan, Thao N. Do, Mohammod N. I. Suvon, Angeline Wang, Lucia Cipolina-Kun, Luigi A. Moretti, Lucas Farndale, Nitisha Jain, Natalia Efremova, Yan Ge, Marta Varela, Hak-Keung Lam, Oya Celiktutan, Ben R. Evans, Alejandro Coca-Castro, Honghan Wu, Zahraa S. Abdallah, Chen Chen, Valentin Danchev, Nataliya Tkachenko, Lei Lu, Tingting Zhu, Gregory G. Slabaugh, Roger K. Moore, William K. Cheung, Peter H. Charlton, Haiping Lu

机构 * Centre for Machine Intelligence, University of Sheffield, Sheffield, UK（机器智能中心，谢菲尔德大学）； School of Computer Science, University of Sheffield, Sheffield, UK（计算机科学学院，谢菲尔德大学）； The Alan Turing Institute, London, UK（艾伦·图灵研究所，伦敦）； Department of Metabolism, Digestion and Reproduction, Imperial College London, London, UK（代谢、消化与生殖部门，伦敦帝国学院）； Department of Applied AI, Simula Research Laboratory, Oslo, Norway（应用人工智能部门，Simula研究实验室，奥斯陆）； Information School, University of Sheffield, Sheffield, UK（信息学院，谢菲尔德大学）； NHS England, Leeds, UK（英国英格兰国家医疗服务体系，利兹）； Institute of Health Informatics, University College London, London, UK（健康信息研究所，伦敦大学学院）； Department of Engineering, King’s College London, London, UK（工程部门，伦敦国王学院）； Department of Computing Science, University of Aberdeen, Aberdeen, UK（计算科学部门，阿伯丁大学）； School of Informatics, University of Edinburgh, Edinburgh, UK（信息学院，爱丁堡大学）； School of Engineering Mathematics and Technology, University of Bristol, Bristol, UK（工程数学与技术学院，布里斯托尔大学）； Department of Informatics, King’s College London, London, UK（信息部门，伦敦国王学院）； Department of Earth Sciences, University of Cambridge, Cambridge, UK（地球科学部门，剑桥大学）； Department of Computer Science, University of Manchester, Manchester, UK（计算机科学部门，曼彻斯特大学）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

2507.17293 2025-09-19 cs.SE cs.LG 62%

Data Virtualization for Machine Learning

Saiful Khan, Joyraj Chakraborty, Philip Beaucamp, Niraj Bhujel, Min Chen

机构 * Scientific Computing, Rutherford Appleton Laboratory Science and Technology Facilities Council (STFC)（科学计算、拉瑟福德-苹果顿实验室科学与技术设施委员会）； Department of Engineering Science, University of Oxford（工程科学系，牛津大学）

专题命中工作流自动化：workflow(abstract)；分类 cs.LG、cs.SE

Journal ref International Conference on Services Computing (SCC 2025)

2509.13487 2025-09-18 cs.SE cs.AI 62%

Prompt2DAG: A Modular Methodology for LLM-Based Data Enrichment Pipeline Generation

Abubakari Alidu, Michele Ciavotta, Flavio DePaoli

机构 * Dept. Informatics, Systems and Communication, University of Milan-Bicocca（信息学、系统与通信系，米兰-比科卡大学）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.SE

2509.13266 2025-09-17 cs.LG cs.AI 62%

JANUS: A Dual-Constraint Generative Framework for Stealthy Node Injection Attacks

Jiahao Zhang, Xiaobing Pei, Zhaokun Zhong, Wenqiang Hao, Zhenghao Tang

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

2502.14043 2025-09-17 cs.LG cs.AI 62%

Safe Learning Under Irreversible Dynamics via Asking for Help

Benjamin Plaut, Juan Liévano-Karim, Hanlin Zhu, Stuart Russell

机构 * Division of Computer Science University of California Berkeley, CA 94720-1776, USA（计算机科学系加州大学伯克利分校）

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments Under submission

2509.07990 2025-09-11 eess.SP cs.AI cs.LG 62%

Signals vs. Videos: Advancing Motion Intention Recognition for Human-Robot Collaboration in Construction

Charan Gajjala Chenchu, Kinam Kim, Gao Lu, Zia Ud Din

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

2509.07933 2025-09-10 cs.SE cs.AI 62%

Breaking Android with AI: A Deep Dive into LLM-Powered Exploitation

Wanni Vidulige Ishan Perera, Xing Liu, Fan liang, Junyi Zhang

机构 * Sam Houston State University（萨姆霍茨州立大学）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.SE

2312.04134 2025-09-09 cs.AI cs.CL 62%

Using a Large Language Model to generate a Design Structure Matrix

Edwin C. Y. Koh

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

Comments 16 pages, 7 Figures, 6 Tables

Journal ref Natural Language Processing Journal, Vol. 9, 2024, Article 100103

2509.05331 2025-09-09 cs.CR cs.AI cs.CL 62%

ForensicsData: A Digital Forensics Dataset for Large Language Models

Youssef Chakir, Iyad Lahsen-Cherif

机构 * INPT, CS department, Rabat, Morocco（INPT计算机科学系，摩洛哥拉巴特）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

Comments Accepted to WiMob 2025 (21st International Conference on Wireless and Mobile Computing, Networking and Communications), Marrakesh, Morocco, Oct 20-22, 2025. 6 pages, 5 figures, 5 tables. IEEEtran conference format

2509.05317 2025-09-09 cs.CV cs.AI cs.HC cs.LG 62%

VILOD: A Visual Interactive Labeling Tool for Object Detection

Isac Holm

机构 * Masters Degree Project（硕士学位项目）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

Comments Master's project

2508.16117 2025-09-05 cs.AI cs.CL cs.IR 62%

Extending FKG.in: Towards a Food Claim Traceability Network

Saransh Kumar Gupta, Rizwan Gulzar Mir, Lipika Dey, Partha Pratim Das, Anirban Sen, Ramesh Jain

机构 * Ashoka University（阿什瓦克大学）； UCI Institute for Future Health（加州未来健康研究所）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

Comments 10 pages, 3 figures, 1 table, 45 references, ACM International Conference on Multimedia 2025 - Multi-modal Food Computing Workshop

2509.02751 2025-09-04 cs.AI cs.DB cs.LG cs.MA 62%

Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics

Matthew Russo, Tim Kraska

机构 * MIT（麻省理工学院）

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments 6 pages, 2 figures, submitted to CIDR'26

2504.11250 2025-09-03 cs.LG cs.AI 62%

A Rollout-Based Algorithm and Reward Function for Resource Allocation in Business Processes

Jeroen Middelhuis, Zaharah Bukhsh, Ivo Adan, Remco Dijkman

机构 * Eindhoven University of Technology Department of Industrial Engineering（埃因霍温理工大学工业工程与创新科学系）

专题命中工作流自动化：agent(abstract)；分类 cs.AI、cs.LG

Comments BPM25 forum

2508.21081 2025-09-01 cs.LG cs.CL 62%

Normalisation of SWIFT Message Counterparties with Feature Extraction and Clustering

Thanasis Schoinas, Benjamin Guinard, Diba Esbati, Richard Chalk

专题命中工作流自动化：workflow(abstract)；分类 cs.CL、cs.LG

2508.20236 2025-08-29 math.HO cs.AI cs.HC cs.LG 62%

The Mathematician's Assistant: Integrating AI into Research Practice

Jonas Henkel

机构 * Fachbereich Mathematik und Informatik, Philipps-Universität Marburg（数学与计算机科学系，马尔堡菲利普斯大学）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

Comments 24 pages, 7 figures. Accepted for publication in Mathematische Semesterberichte (to appear in vol. 72, no. 2)

2508.20217 2025-08-29 cs.CL cs.AI 62%

Prompting Strategies for Language Model-Based Item Generation in K-12 Education: Bridging the Gap Between Small and Large Language Models

Mohammad Amini, Babak Ahmadi, Xiaomeng Xiong, Yilin Zhang, Christopher Qiao

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.CL

2508.20030 2025-08-28 eess.SY cs.AI cs.AR cs.LG cs.SY 62%

Large Language Models (LLMs) for Electronic Design Automation (EDA)

Kangwei Xu, Denis Schwachhofer, Jason Blocklove, Ilia Polian, Peter Domanski, Dirk Pflüger, Siddharth Garg, Ramesh Karri, Ozgur Sinanoglu, Johann Knechtel, Zhuorui Zhao, Ulf Schlichtmann, Bing Li

机构 * Technical University of Munich（慕尼黑技术大学）； University of Stuttgart（斯图加特大学）； New York University（纽约大学）； University of Siegen（锡根大学）

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

Comments Accepted by IEEE International System-on-Chip Conference

2505.24073 2025-08-27 cs.AI cs.CL cs.CV 62%

mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation

Chan-Wei Hu, Yueqi Wang, Shuo Xing, Chia-Ju Chen, Suofei Feng, Ryan Rossi, Zhengzhong Tu

机构 * Texas A&M University（德克萨斯农工大学）； University of California, Berkeley（加州大学伯克利分校）； University of Texas at Austin（德克萨斯大学奥斯汀分校）； Stanford University（斯坦福大学）； Adobe Research（Adobe研究院）

专题命中工作流自动化：agentic(abstract)；分类 cs.AI、cs.CL

Comments 16 pages

2401.13796 2025-08-21 cs.LG cs.AI 62%

Don't Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning

Andrea Apicella, Francesco Isgrò, Roberto Prevete

专题命中工作流自动化：workflow(abstract)；分类 cs.AI、cs.LG

Comments Published on Artificial Intelligence Review journal. The paper is in Open Access available at https://link.springer.com/article/10.1007/s10462-025-11326-3

Journal ref Artificial Intelligence Review, 2025

1. 工作流自动化 10469 篇

Provably Invincible Adversarial Attacks on Reinforcement Learning Systems: A Rate-Distortion Information-Theoretic Approach

Repurposing Annotation Guidelines to Instruct LLM Annotators: A Case Study

A Cooperative Approach for Knowledge-based Business Process Design in a Public Authority

Assessing Large Language Models for Structured Medical Order Extraction

Deceptive Exploration in Multi-armed Bandits

DeepOHeat-v1: Efficient Operator Learning for Fast and Trustworthy Thermal Simulation and Optimization in 3D-IC Design

Topology-Aware and Highly Generalizable Deep Reinforcement Learning for Efficient Retrieval in Multi-Deep Storage Systems

NEURODNAAI: Neural pipeline approaches for the advancing dna-based information storage as a sustainable digital medium using deep learning framework

Fine-tuning with RAG for Improving LLM Learning of New Skills

Automatic Speech Recognition for Greek Medical Dictation

Type-Compliant Adaptation Cascades: Adapting Programmatic LM Workflows to Data

Towards deployment-centric multimodal AI beyond vision and language

Data Virtualization for Machine Learning

Prompt2DAG: A Modular Methodology for LLM-Based Data Enrichment Pipeline Generation

JANUS: A Dual-Constraint Generative Framework for Stealthy Node Injection Attacks

Safe Learning Under Irreversible Dynamics via Asking for Help

Signals vs. Videos: Advancing Motion Intention Recognition for Human-Robot Collaboration in Construction

Breaking Android with AI: A Deep Dive into LLM-Powered Exploitation

Using a Large Language Model to generate a Design Structure Matrix

ForensicsData: A Digital Forensics Dataset for Large Language Models

VILOD: A Visual Interactive Labeling Tool for Object Detection

Extending FKG.in: Towards a Food Claim Traceability Network

Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics

A Rollout-Based Algorithm and Reward Function for Resource Allocation in Business Processes

Normalisation of SWIFT Message Counterparties with Feature Extraction and Clustering

The Mathematician's Assistant: Integrating AI into Research Practice

Prompting Strategies for Language Model-Based Item Generation in K-12 Education: Bridging the Gap Between Small and Large Language Models

Large Language Models (LLMs) for Electronic Design Automation (EDA)

mRAG: Elucidating the Design Space of Multi-modal Retrieval-Augmented Generation

Don't Push the Button! Exploring Data Leakage Risks in Machine Learning and Transfer Learning