AI Agent - arXivDaily 专题

2207.02726 2025-08-21 cs.LG cs.AI cs.HC eess.SP 62%

Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users

Ana Lucic, Sheeraz Ahmad, Amanda Furtado Brinhosa, Vera Liao, Himani Agrawal, Umang Bhatt, Krishnaram Kenthapadi, Alice Xiang, Maarten de Rijke, Nicholas Drabowski

机构 * University of Amsterdam, Netherlands（阿姆斯特丹大学）； Google, USA（谷歌）； Microsoft Research, Canada（微软研究院）； University of Cambridge, United Kingdom（剑桥大学）

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

Comments Accepted to ICML 2022 Workshop on Interpretable ML in Healthcare

2307.14740 2025-08-19 cs.SE cs.AI 62%

New Interaction Paradigm for Complex EDA Software Leveraging GPT

Xinyu Wang, Boyu Han, Zhenghan Tai, Jingrui Tian, Yifan Wang, Junyu Yan, Yidong Tian

机构 * McGill University, Canada（麦吉尔大学）； Stanford University, USA（斯坦福大学）； University of Toronto, Canada（多伦多大学）； Tsinghua University, China（清华大学）； Beihang University, China（北航大学）； The University of Manchester, UK（曼彻斯特大学）； University of California, Los Angeles, USA（加州大学洛杉矶分校）； Beijing Smarton Empower Co., Ltd., China（北京Smarton赋能科技有限公司）

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

Comments Accepted to ICML 2025 Workshop on New In Machine Learning (NewInML), 9 pages, 8 figures

2508.12027 2025-08-19 cs.AI cs.LG q-bio.NC 62%

Active inference for action-unaware agents

Filippo Torresan, Keisuke Suzuki, Ryota Kanai, Manuel Baltieri

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

Comments 59 pages, 47 figures

2508.02029 2025-08-19 cs.LG cs.AI 62%

A Confidence-Diversity Framework for Calibrating AI Judgement in Accessible Qualitative Coding Tasks

Zhilong Zhao, Yindi Liu

机构 * School of Journalism and Communication, South China University of Technology, Guangzhou, China（新闻与传播学院，华南理工大学，广州，中国）； Guangdong–Hong Kong–Macao Greater Bay Area Research Institute of International Communication, South China University of Technology, Guangzhou, China（粤港澳大湾区国际传播研究院，华南理工大学，广州，中国）

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

Comments 23 pages, 5 figures. Code and data available at https://doi.org/10.7910/DVN/G1AYGK

2508.10701 2025-08-15 cs.LG cs.AI 62%

REFN: A Reinforcement-Learning-From-Network Framework against 1-day/n-day Exploitations

Tianlong Yu, Lihong Liu, Ziyi Zhou, Fudu Xing, Kailong Wang, Yang Yang

机构 * School of Artificial Intelligence, Hubei University（湖北大学人工智能学院）； Huazhong University of Science and Technology（华中科技大学）； University of Southern California（美国南加州大学）

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

2508.10492 2025-08-15 cs.AI cs.CE cs.CL 62%

Reverse Physician-AI Relationship: Full-process Clinical Diagnosis Driven by a Large Language Model

Shicheng Xu, Xin Huang, Zihao Wei, Liang Pang, Huawei Shen, Xueqi Cheng

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, CAS（人工智能安全国家重点实验室，计算技术研究所，中国科学院）； University of Chinese Academy of Sciences（中国科学院大学）； Peking University Third Hospital（北京大学第三医院）

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

Comments 39 pages

2508.09960 2025-08-14 cs.RO cs.AI cs.LG 62%

GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation

Yifei Yao, Chengyuan Luo, Jiaheng Du, Wentao He, Jun-Guo Lu

机构 * SJTU MVASL Lab, Department of Automation, Shanghai Jiao Tong University（上海交通大学自动化系）

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

2507.21065 2025-08-13 cs.CL cs.HC cs.LG cs.RO 62%

AI Pedagogy: Dialogic Social Learning for Artificial Agents

Sabrina Patania, Luca Annese, Cansu Koyuturk, Azzurra Ruggeri, Dimitri Ognibene

机构 * University of Milan-Bicocca（米兰-比科卡大学）； Technical University of Munich（慕尼黑技术大学）； Institute for Cognitive Sciences and Technologies (ISTC-CNR)（认知科学与技术研究所（ISTC-CNR））

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

Comments accepted at ICSR2025

2508.01612 2025-08-05 cs.LG cs.AI 62%

Augmented Reinforcement Learning Framework For Enhancing Decision-Making In Machine Learning Models Using External Agents

Sandesh Kumar Singh

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

Comments Master's thesis, 274 pages, 8 Tables, 73 figures

2508.00106 2025-08-04 cs.AI cs.LG cs.LO cs.SY eess.SY 62%

Hyperproperty-Constrained Secure Reinforcement Learning

Ernest Bonnah, Luan Viet Nguyen, Khaza Anuarul Hoque

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

Comments Accepted in IEEE/ACM MEMOCODE 2025

2507.22915 2025-08-01 cs.CL cs.AI 62%

Theoretical Foundations and Mitigation of Hallucination in Large Language Models

Esmail Gumaan

机构 * Department of Computer Science, University of Sana'a（桑加大学计算机科学系）

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

Comments 12 pages

2507.22064 2025-07-31 cs.SE cs.AI 62%

Machine Learning Experiences: A story of learning AI for use in enterprise software testing that can be used by anyone

Michael Cohoon, Debbie Furman

机构 * IBM Systems（IBM系统）

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

2507.18742 2025-07-28 cs.CL cs.AI 62%

Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement

Víctor Gallego

机构 * Komorebi AI Technologies（Komorebi人工智能技术）

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

Comments Accepted to SCALR Workshop @ COLM 2025

2507.18223 2025-07-25 cs.SE cs.AI 62%

GenAI for Automotive Software Development: From Requirements to Wheels

Nenad Petrovic, Fengjunjie Pan, Vahid Zolfaghari, Krzysztof Lebioda, Andre Schamschurko, Alois Knoll

机构 * Technical University of Munich, Germany（慕尼黑技术大学，德国）

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

2507.16586 2025-07-23 cs.HC cs.AI cs.SE 62%

AI for Better UX in Computer-Aided Engineering: Is Academia Catching Up with Industry Demands? A Multivocal Literature Review

Choro Ulan Uulu, Mikhail Kulyabin, Layan Etaiwi, Nuno Miguel Martins Pacheco, Jan Joosten, Kerstin Röse, Filippos Petridis, Jan Bosch, Helena Holmström Olsson

机构 * Siemens AG（西门子公司）； Chalmers University of Technology（查尔姆斯理工大学）； Eindhoven University of Technology（埃因霍温理工大学）； Malmö University（马尔默大学）

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

2507.15772 2025-07-22 cs.LG cs.AI q-bio.BM 62%

Deep-Learning Investigation of Vibrational Raman Spectra for Plant-Stress Analysis

Anoop C. Patil, Benny Jian Rong Sng, Yu-Wei Chang, Joana B. Pereira, Chua Nam-Hai, Rajani Sarojam, Gajendra Pratap Singh, In-Cheol Jang, Giovanni Volpe

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

Comments *Authors contributed equally to this work. +Supervised this work. 5 main figures and 1 extended data figure in manuscript. The PDF includes supplementary material

2407.09975 2025-07-16 cs.CY cs.AI cs.CL stat.AP 62%

The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters Exam Performances

Allen Nie, Yash Chandak, Miroslav Suzara, Ali Malik, Juliette Woodrow, Matt Peng, Mehran Sahami, Emma Brunskill, Chris Piech

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

Comments 32 pages. Published at L@S 2025

2507.09100 2025-07-15 cs.HC cs.AI cs.CL 62%

AInsight: Augmenting Expert Decision-Making with On-the-Fly Insights Grounded in Historical Data

Mohammad Abolnejadian, Shakiba Amirshahi, Matthew Brehmer, Anamaria Crisan

机构 * Cheriton School of Computer Science（切里顿计算机科学学院）； University of Waterloo（滑铁卢大学）

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

Comments 7 pages and 4 figures. Proceedings of the 7th ACM Conference on Conversational User Interfaces (CUI '25)

2507.07910 2025-07-15 cs.CL cs.AI cs.IR 62%

DTECT: Dynamic Topic Explorer & Context Tracker

Suman Adhya, Debarshi Kumar Sanyal

机构 * Indian Association for the Cultivation of Science（印度科学培养协会）

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

Comments Code: https://github.com/AdhyaSuman/DTECT | Demo: https://huggingface.co/spaces/AdhyaSuman/DTECT | Video: https://youtu.be/B8nNfxFoJAU

2507.08575 2025-07-14 cs.AI cs.CL cs.CV 62%

Large Multi-modal Model Cartographic Map Comprehension for Textual Locality Georeferencing

Kalana Wijegunarathna, Kristin Stock, Christopher B. Jones

机构 * School of Mathematical and Computational Sciences, Massey University, Auckland, New Zealand（梅西大学数学与计算科学学院）； School of Computer Science and Informatics, Cardiff University, Cardiff, UK（卡迪夫大学计算机科学与信息学院）

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

2502.05638 2025-07-09 cs.CL cs.AI 62%

ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports

Aynur Guluzade, Naguib Heiba, Zeyd Boukhers, Florim Hamiti, Jahid Hasan Polash, Yehya Mohamad, Carlos A Velasco

机构 * Fraunhofer Institute for Applied Information Technology（弗劳恩霍夫应用信息科技研究所）

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

2507.03811 2025-07-08 cs.AI cs.CY cs.LG 62%

Leveraging Large Language Models for Tacit Knowledge Discovery in Organizational Contexts

Gianlucca Zuin, Saulo Mastelini, Túlio Loures, Adriano Veloso

机构 * Universidade Federal de Minas Gerais (UFMG)（巴西联邦大学矿务学院）； Instituto de Ciências Matemáticas e de Computação, Universidade de São Paulo (ICMC-USP)（圣保罗大学数学与计算机科学研究所）； Kunumi（Kunumi公司）

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

Comments 8 pages, 4 figures, accepted to International Joint Conference on Neural Networks (IJCNN) 2025

2507.01663 2025-07-03 cs.LG cs.AI 62%

AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

Zhenyu Han, Ansheng You, Haibo Wang, Kui Luo, Guang Yang, Wenqi Shi, Menglong Chen, Sicheng Zhang, Zeshun Lan, Chunshi Deng, Huazhong Ji, Wenjie Liu, Yu Huang, Yixiang Zhang, Chenyi Pan, Jing Wang, Xin Huang, Chunsheng Li, Jianping Wu

机构 * Huawei（华为）； Huawei Individual Researcher（华为独立研究者）； Individual Researcher（独立研究者）

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

2507.00180 2025-07-02 cs.AI cs.LG 62%

BlackBoxToBlueprint: Extracting Interpretable Logic from Legacy Systems using Reinforcement Learning and Counterfactual Analysis

Vidhi Rathore

机构 * IIIT Hyderabad

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

2507.00048 2025-07-02 cs.AI cond-mat.mtrl-sci cs.CE cs.LG 62%

A collaborative digital twin built on FAIR data and compute infrastructure

Thomas M. Deucher, Juan C. Verduzco, Michael Titus, Alejandro Strachan

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

Comments 10 pages, 5 figures

2506.21813 2025-06-30 cs.CV cs.AI cs.LG 62%

CAT-SG: A Large Dynamic Scene Graph Dataset for Fine-Grained Understanding of Cataract Surgery

Felix Holm, Gözde Ünver, Ghazal Ghazaei, Nassir Navab

机构 * Chair for Computer-Aided Medical Procedures, Technical University Munich, Germany（计算机辅助医疗程序研究所，慕尼黑技术大学，德国）； Carl Zeiss AG, Munich, Germany（蔡司股份公司，慕尼黑，德国）

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

2407.02508 2025-06-26 cs.RO cs.AI cs.LG 62%

Physics-informed Imitative Reinforcement Learning for Real-world Driving

Hang Zhou, Yihao Qin, Dan Xu, Yiding Ji

机构 * Robotics and Autonomous Systems Thrust, Systems Hub, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）机器人与自主系统 thrust、系统枢纽）； Department of Computer Science and Engineering, School of Engineering, The Hong Kong University of Science and Technology（香港科技大学计算机科学与工程系、工程学院）

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

2506.19290 2025-06-25 cs.AI cs.CL 62%

Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs

Liang Zeng, Yongcong Li, Yuzhen Xiao, Changshi Li, Chris Yuhao Liu, Rui Yan, Tianwen Wei, Jujie He, Xuchen Song, Yang Liu, Yahui Zhou

机构 * Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs（Skywork-SWE：揭示软件工程中大语言模型的数据扩展规律）

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

2506.16731 2025-06-23 cs.AI cs.DC cs.LG 62%

Incentivizing High-quality Participation From Federated Learning Agents

Jinlong Pang, Jiaheng Wei, Yifan Hua, Chen Qian, Yang Liu

机构 * University of California, Santa Cruz（加州大学圣克鲁兹分校）； The Hong Kong University of Science and Technology (Guangzhou)（香港理工大学（广州））

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

2506.04287 2025-06-23 cs.AI cs.LG 62%

Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback

Yongjin Yang, Sinjae Kang, Juyong Lee, Dongjun Lee, Se-Young Yun, Kimin Lee

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

Comments Preprint, under review

1. 工作流自动化 10469 篇

Towards the Use of Saliency Maps for Explaining Low-Quality Electrocardiograms to End Users

New Interaction Paradigm for Complex EDA Software Leveraging GPT

Active inference for action-unaware agents

A Confidence-Diversity Framework for Calibrating AI Judgement in Accessible Qualitative Coding Tasks

REFN: A Reinforcement-Learning-From-Network Framework against 1-day/n-day Exploitations

Reverse Physician-AI Relationship: Full-process Clinical Diagnosis Driven by a Large Language Model

GBC: Generalized Behavior-Cloning Framework for Whole-Body Humanoid Imitation

AI Pedagogy: Dialogic Social Learning for Artificial Agents

Augmented Reinforcement Learning Framework For Enhancing Decision-Making In Machine Learning Models Using External Agents

Hyperproperty-Constrained Secure Reinforcement Learning

Theoretical Foundations and Mitigation of Hallucination in Large Language Models

Machine Learning Experiences: A story of learning AI for use in enterprise software testing that can be used by anyone

Specification Self-Correction: Mitigating In-Context Reward Hacking Through Test-Time Refinement

GenAI for Automotive Software Development: From Requirements to Wheels

AI for Better UX in Computer-Aided Engineering: Is Academia Catching Up with Industry Demands? A Multivocal Literature Review

Deep-Learning Investigation of Vibrational Raman Spectra for Plant-Stress Analysis

The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters Exam Performances

AInsight: Augmenting Expert Decision-Making with On-the-Fly Insights Grounded in Historical Data

DTECT: Dynamic Topic Explorer & Context Tracker

Large Multi-modal Model Cartographic Map Comprehension for Textual Locality Georeferencing

ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports

Leveraging Large Language Models for Tacit Knowledge Discovery in Organizational Contexts

AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

BlackBoxToBlueprint: Extracting Interpretable Logic from Legacy Systems using Reinforcement Learning and Counterfactual Analysis

A collaborative digital twin built on FAIR data and compute infrastructure

CAT-SG: A Large Dynamic Scene Graph Dataset for Fine-Grained Understanding of Cataract Surgery

Physics-informed Imitative Reinforcement Learning for Real-world Driving

Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs

Incentivizing High-quality Participation From Federated Learning Agents

Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback