AI Agent

Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development

Daoyuan Chen, Haibin Wang, Yilun Huang, Ce Ge, Yaliang Li, Bolin Ding, Jingren Zhou

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

Comments Accepted by ICML 2025 (Spotlight). 33 pages, 16 tables, 14 figures

TestAgent: An Adaptive and Intelligent Expert for Human Assessment

Junhao Yu, Yan Zhuang, YuXuan Sun, Weibo Gao, Qi Liu, Mingyue Cheng, Zhenya Huang, Enhong Chen

机构 * State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学） ； Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（人工智能研究院，合肥综合性国家科学中心） 纠错

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

Comments 24 pages,10 figures

Content Moderation by LLM: From Accuracy to Legitimacy

Tao Huang

机构 * City University of Hong Kong（香港城市大学） 纠错

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

Modelling bounded rational decision-making through Wasserstein constraints

Benjamin Patrick Evans, Leo Ardon, Sumitra Ganesh

机构 * JP Morgan AI Research（摩根大通人工智能研究） 纠错

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

Comments Accepted at RLDM 2025

Generative AI in Health Economics and Outcomes Research: A Taxonomy of Key Definitions and Emerging Applications, an ISPOR Working Group Report

Rachael Fleurence, Xiaoyan Wang, Jiang Bian, Mitchell K. Higashi, Turgay Ayer, Hua Xu, Dalia Dawoud, Jagpreet Chhatwal

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

Comments 36 pages, 1 figure, 2 tables

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment

Chaoqi Wang, Zhuokai Zhao, Yibo Jiang, Zhaorun Chen, Chen Zhu, Yuxin Chen, Jiayi Liu, Lizhu Zhang, Xiangjun Fan, Hao Ma, Sinong Wang

机构 * Meta ； University of Chicago（芝加哥大学） 纠错

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

Natural Language Processing in Support of Evidence-based Medicine: A Scoping Review

Zihan Xu, Haotian Ma, Gongbo Zhang, Yihao Ding, Chunhua Weng, Yifan Peng

机构 * Weill Cornell Medicine（韦尔·科恩医学中心） ； Columbia University（哥伦比亚大学） ； University of Sydney（悉尼大学） 纠错

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

Comments Accepted by ACL 2025 Findings

LEGO-Compiler: Enhancing Neural Compilation Through Translation Composability

Shuoming Zhang, Jiacheng Zhao, Chunwei Xia, Zheng Wang, Yunji Chen, Xiaobing Feng, Huimin Cui

机构 * SKLP, Institute of Computing Technology, CAS University of Chinese Academy of Sciences, Beijing, China（SKLP，计算技术研究所，中国科学院大学，北京，中国） ； University of Leeds, UK（利兹大学，英国） ； Zhongguancun Laboratory, Beijing, China（中关村实验室，北京，中国） 纠错

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

Comments 30 pages, 8 figures, 4 tables. Preprint. Under review

KnowTrace: Bootstrapping Iterative Retrieval-Augmented Generation with Structured Knowledge Tracing

Rui Li, Quanyu Dai, Zeyu Zhang, Xu Chen, Zhenhua Dong, Ji-Rong Wen

机构 * Gaoling School of Artificial Intelligence（人工智能学院） ； Renmin University of China（中国人民大学） ； Huawei Noah’s Ark Lab（华为诺亚实验室） 纠错

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

Comments Accepted by KDD 2025

Malware families discovery via Open-Set Recognition on Android manifest permissions

Filippo Leveni, Matteo Mistura, Francesco Iubatti, Carmine Giangregorio, Nicolò Pastore, Cesare Alippi, Giacomo Boracchi

机构 * Department of Electronics, Information and Bioengineering（电子、信息与生物工程系） ； Faculty of Informatics（信息学院） ； Cleafy S.p.A.（Cleafy公司） 纠错

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

Comments Submitted to European Conference on Artificial Intelligence (ECAI 2025)

GNN-Suite: a Graph Neural Network Benchmarking Framework for Biomedical Informatics

Sebestyén Kamp, Giovanni Stracquadanio, T. Ian Simpson

机构 * School of Informatics University of Edinburgh（信息学院爱丁堡大学） ； School of Biological Sciences University of Edinburgh（生物科学学院爱丁堡大学） 纠错

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

Comments Main article 8 pages (20 in total with supplementary information included), 3 main article figures and 3 supplemental figures

Characterizing the Investigative Methods of Fictional Detectives with Large Language Models

Edirlei Soares de Lima, Marco A. Casanova, Bruno Feijó, Antonio L. Furtado

机构 * Academy for AI, Games and Media（人工智能、游戏与媒体学院） ； Breda University of Applied Sciences（布雷达应用科学大学） ； Department of Informatics PUC-Rio（信息学院（PUC-Rio）） 纠错

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

Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications

Maria Despoina Siampou, Jialiang Li, John Krumm, Cyrus Shahabi, Hua Lu

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

Lean Copilot: Large Language Models as Copilots for Theorem Proving in Lean

Peiyang Song, Kaiyu Yang, Anima Anandkumar

机构 * California Institute of Technology（加州理工学院） 纠错

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

Comments Published at NeuS 2025. All code and artifacts open-sourced at https://github.com/lean-dojo/LeanCopilot. All evaluation details are made public at https://github.com/Peiyang-Song/mathematics_in_lean/tree/full-scale-experiment

HiPerRAG: High-Performance Retrieval Augmented Generation for Scientific Insights

Ozan Gokdemir, Carlo Siebenschuh, Alexander Brace, Azton Wells, Brian Hsu, Kyle Hippe, Priyanka V. Setty, Aswathy Ajith, J. Gregory Pauloski, Varuni Sastry, Sam Foreman, Huihuo Zheng, Heng Ma, Bharat Kale, Nicholas Chia, Thomas Gibbs, Michael E. Papka, Thomas Brettin, Francis J. Alexander, Anima Anandkumar, Ian Foster, Rick Stevens, Venkatram Vishwanath, Arvind Ramanathan

机构 * Argonne National Laboratory（阿贡国家实验室） ； The University of Chicago（芝加哥大学） ； NVIDIA Inc.（NVIDIA公司） ； University of Illinois Chicago（伊利诺伊大学芝加哥分校） ； California Institute of Technology（加州理工学院） 纠错

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

Comments This paper has been accepted at the Platform for Advanced Scientific Computing Conference (PASC 25), June 16-18, 2025, Brugg-Windisch, Switzerland

Aligning Large Language Models with Healthcare Stakeholders: A Pathway to Trustworthy AI Integration

Kexin Ding, Mu Zhou, Akshay Chaudhari, Shaoting Zhang, Dimitris N. Metaxas

机构 * Rutgers University（罗格斯大学） ； Stanford University（斯坦福大学） ； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室） 纠错

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

MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans

Huangyue Yu, Baoxiong Jia, Yixin Chen, Yandan Yang, Puhao Li, Rongpeng Su, Jiaxin Li, Qing Li, Wei Liang, Song-Chun Zhu, Tengyu Liu, Siyuan Huang

机构 * State Key Laboratory of General Artificial Intelligence, BIGAI（通用人工智能国家重点实验室，BIGAI） ； Beijing Institute of Technology（北京理工大学） ； Tsinghua University（清华大学） ； University of Science and Technology of China（中国科学技术大学） 纠错

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

Comments CVPR 2025

Reduced-order structure-property linkages for stochastic metamaterials

Hooman Danesh, Maruthi Annamaraju, Tim Brepols, Stefanie Reese, Surya R. Kalidindi

机构 * Institute of Applied Mechanics, RWTH Aachen University（亚琛工业大学应用力学研究所） ； George W. Woodruff School of Mechanical Engineering, Georgia Institute of Technology（佐治亚理工学院乔治·W·伍德鲁夫机械工程学院） ； University of Siegen（锡根大学） 纠错

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

AI-Enhanced Automatic Design of Efficient Underwater Gliders

Peter Yichen Chen, Pingchuan Ma, Niklas Hagemann, John Romanishin, Wei Wang, Daniela Rus, Wojciech Matusik

机构 * MIT CSAIL（MIT计算机科学与人工智能实验室） ； Marine Robotics Lab（海洋机器人实验室） ； University of Wisconsin-Madison（威斯康星大学麦迪逊分校） 纠错

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

LLM Enhancer: Merged Approach using Vector Embedding for Reducing Large Language Model Hallucinations with External Knowledge

Naheed Rayhan, Md. Ashrafuzzaman

机构 * Department of Computer Science and Engineering, Jagannath University（计算机科学与工程系，贾甘纳思大学） 纠错

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

Closing the Gap: A User Study on the Real-world Usefulness of AI-powered Vulnerability Detection & Repair in the IDE

Benjamin Steenhoek, Kalpathy Sivaraman, Renata Saldivar Gonzalez, Yevhen Mohylevskyy, Roshanak Zilouchian Moghaddam, Wei Le

机构 * Department of Computer Science, Iowa State University（计算机科学系，爱荷华州立大学） ； Microsoft Data & AI（微软数据与人工智能） 纠错

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

Comments Accepted to ICSE 2025 research track. Camera-ready version with grant reference number fixed in acknowledgments

PTCL: Pseudo-Label Temporal Curriculum Learning for Label-Limited Dynamic Graph

Shengtao Zhang, Haokai Zhang, Shiqi Lou, Zicheng Wang, Zinan Zeng, Yilin Wang, Minnan Luo

机构 * Xi’an Jiaotong University（西安交通大学） 纠错

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

Comments 13 pages, 5 figures

Optimizing RLHF Training for Large Language Models with Stage Fusion

Yinmin Zhong, Zili Zhang, Bingyang Wu, Shengyu Liu, Yukun Chen, Changyi Wan, Hanpeng Hu, Lei Xia, Ranchen Ming, Yibo Zhu, Xin Jin

机构 * School of Computer Science, Peking University（北京大学计算机学院） 纠错

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

Systems with Switching Causal Relations: A Meta-Causal Perspective

Moritz Willig, Tim Nelson Tobiasch, Florian Peter Busch, Jonas Seng, Devendra Singh Dhami, Kristian Kersting

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

Comments 21 pages, 3 figures, 4 tables, ICLR 2025 Camera Ready Version

Possibility for Proactive Anomaly Detection

Jinsung Jeon, Jaehyeon Park, Sewon Park, Jeongwhan Choi, Minjung Kim, Noseong Park

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

Comments Accepted at ICLR 2025 I Can't Believe It's Not Better: Challenges in Applied Deep Learning Workshop (ICBINB)

Can Large Language Models Replace Data Scientists in Biomedical Research?

Zifeng Wang, Benjamin Danek, Ziwei Yang, Zheng Chen, Jimeng Sun

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

Improving Mixed-Criticality Scheduling with Reinforcement Learning

Muhammad El-Mahdy, Nourhan Sakr, Rodrigo Carrasco

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

Comments This work was submitted to the 32nd International Conference on Real-Time Networks and Systems (RTNS) on June 8, 2024

BRIDGES: Bridging Graph Modality and Large Language Models within EDA Tasks

Wei Li, Yang Zou, Christopher Ellis, Ruben Purdy, Shawn Blanton, José M. F. Moura

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

From Automation to Autonomy in Smart Manufacturing: A Bayesian Optimization Framework for Modeling Multi-Objective Experimentation and Sequential Decision Making

Avijit Saha Asru, Hamed Khosravi, Imtiaz Ahmed, Abdullahil Azeem

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

Journal ref International Journal of Advanced Manufacturing Technology (2025)

Generating Structured Plan Representation of Procedures with LLMs

Deepeka Garg, Sihan Zeng, Sumitra Ganesh, Leo Ardon

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