AI Agent

WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning

Zimu Lu, Houxing Ren, Yunqiao Yang, Ke Wang, Zhuofan Zong, Junting Pan, Mingjie Zhan, Hongsheng Li

机构 * Multimedia Laboratory (MMLab)（多媒体实验室） 纠错

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

AEGIS: An Agent for Extraction and Geographic Identification in Scholarly Proceedings

Om Vishesh, Harshad Khadilkar, Deepak Akkil

机构 * Central University of Jharkhand（贾本德中央大学） 纠错

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

Comments 5 pages, 2 figures

TAGAL: Tabular Data Generation using Agentic LLM Methods

Benoît Ronval, Pierre Dupont, Siegfried Nijssen

机构 * UCLouvain（乌尔特里大学） ； ICTEAM（信息与团队研究所） ； KU Leuven（根特大学） ； DTAI（数据与人工智能研究所） 纠错

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

A-SEA3L-QA: A Fully Automated Self-Evolving, Adversarial Workflow for Arabic Long-Context Question-Answer Generation

Kesen Wang, Daulet Toibazar, Pedro J. Moreno

机构 * Humain 纠错

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

Automating the Deep Space Network Data Systems; A Case Study in Adaptive Anomaly Detection through Agentic AI

Evan J. Chou, Lisa S. Locke, Harvey M. Soldan

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

A Comprehensive Perspective on Explainable AI across the Machine Learning Workflow

George Paterakis, Andrea Castellani, George Papoutsoglou, Tobias Rodemann, Ioannis Tsamardinos

机构 * JADBio Gnosis DA S.A.（JADBio Gnosis DA公司） ； Honda Research Institute Europe（本田研究院欧洲分部） ； University of Crete（希腊克里特大学） 纠错

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

Comments Preprint. Currently under review at "Artificial Intelligence Review" journal

A Practical Approach for Building Production-Grade Conversational Agents with Workflow Graphs

Chiwan Park, Wonjun Jang, Daeryong Kim, Aelim Ahn, Kichang Yang, Woosung Hwang, Jihyeon Roh, Hyerin Park, Hyosun Wang, Min Seok Kim, Jihoon Kang

机构 * Kakao 纠错

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

Comments Accepted to ACL 2025 Industry Track. 12 pages, 5 figures

Self-Taught Agentic Long Context Understanding

Yufan Zhuang, Xiaodong Yu, Jialian Wu, Ximeng Sun, Ze Wang, Jiang Liu, Yusheng Su, Jingbo Shang, Zicheng Liu, Emad Barsoum

机构 * AMD ； UC San Diego（加州大学圣地亚哥分校） 纠错

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

Comments Published at ACL 2025 Main Conference

Data-Copilot: Bridging Billions of Data and Humans with Autonomous Workflow

Wenqi Zhang, Yongliang Shen, Zeqi Tan, Guiyang Hou, Weiming Lu, Yueting Zhuang

机构 * College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院） 纠错

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

Self-Explanation in Social AI Agents

Rhea Basappa, Mustafa Tekman, Hong Lu, Benjamin Faught, Sandeep Kakar, Ashok K. Goel

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

Comments Extended version of the paper published in International Conference on Intelligent Tutoring Systems, pages 351-360, 2024, Springer. Images corrected, and live deployment, ablation, and precision study results added

LearningFlow: Automated Policy Learning Workflow for Urban Driving with Large Language Models

Zengqi Peng, Yubin Wang, Xu Han, Lei Zheng, Jun Ma

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

An Agentic Approach to Automatic Creation of P&ID Diagrams from Natural Language Descriptions

Shreeyash Gowaikar, Srinivasan Iyengar, Sameer Segal, Shivkumar Kalyanaraman

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

Comments Accepted at the AAAI'25 Workshop on AI to Accelerate Science and Engineering (AI2ASE)

Accelerating Manufacturing Scale-Up from Material Discovery Using Agentic Web Navigation and Retrieval-Augmented AI for Process Engineering Schematics Design

Sakhinana Sagar Srinivas, Akash Das, Shivam Gupta, Venkataramana Runkana

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

ScribeAgent: Towards Specialized Web Agents Using Production-Scale Workflow Data

Junhong Shen, Atishay Jain, Zedian Xiao, Ishan Amlekar, Mouad Hadji, Aaron Podolny, Ameet Talwalkar

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

Model-based Workflow for the Automated Generation of PDDL Descriptions

Hamied Nabizada, Tom Jeleniewski, Felix Gehlhoff, Alexander Fay

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

Journal ref 2024 IEEE 29th International Conference on Emerging Technologies and Factory Automation (ETFA)

HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction

Qianyue Hao, Jingyang Fan, Fengli Xu, Jian Yuan, Yong Li

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

Comments NeurIPS 2024 paper

Automated Red Teaming with GOAT: the Generative Offensive Agent Tester

Maya Pavlova, Erik Brinkman, Krithika Iyer, Vitor Albiero, Joanna Bitton, Hailey Nguyen, Joe Li, Cristian Canton Ferrer, Ivan Evtimov, Aaron Grattafiori

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

Towards Integrating Epistemic Uncertainty Estimation into the Radiotherapy Workflow

Marvin Tom Teichmann, Manasi Datar, Lisa Kratzke, Fernando Vega, Florin C. Ghesu

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

Comments Keywords: Epistemic Uncertainty - Out-of-Distribution Detection - CT Segmentation - OAR contouring - Radiotherapy

TrafficGPT: Towards Multi-Scale Traffic Analysis and Generation with Spatial-Temporal Agent Framework

Jinhui Ouyang, Yijie Zhu, Xiang Yuan, Di Wu

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

Self-Initiated Open World Learning for Autonomous AI Agents

Bing Liu, Eric Robertson, Scott Grigsby, Sahisnu Mazumder

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

Comments Published in AAAI 2022 Spring Symposium Series

LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing

Bryan Wang, Yuliang Li, Zhaoyang Lv, Haijun Xia, Yan Xu, Raj Sodhi

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

Comments Paper accepted to the ACM Conference on Intelligent User Interfaces (ACM IUI) 2024

Agent AI: Surveying the Horizons of Multimodal Interaction

Zane Durante, Qiuyuan Huang, Naoki Wake, Ran Gong, Jae Sung Park, Bidipta Sarkar, Rohan Taori, Yusuke Noda, Demetri Terzopoulos, Yejin Choi, Katsushi Ikeuchi, Hoi Vo, Li Fei-Fei, Jianfeng Gao

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

From Admission to Invariants: Measuring Deviation in Delegated Agent Systems

从准入到不变量：在委托代理系统中测量偏差

Marcelo Fernandez

机构 * TraslaIA 纠错

专题命中 工作流自动化 ：agent(title,abstract)；autonomous agent(abstract)；分类 cs.AI

AI总结 研究探讨了委托代理系统中执法机制无法检测准入时设定的行为空间的问题，提出了不变量测量层（IML）以恢复可观测性并实现有限延迟的偏差检测。

Comments 21 pages, 6 figures. 3rd paper (Paper 2) in the 6-paper Agent Governance Series (Papers 0-5). Zenodo: https://doi.org/10.5281/zenodo.19672589. Companion: P0 (arXiv:2604.17511), P1/ACP (arXiv:2603.18829), P3 (zenodo.19672597), P4 (zenodo.19672608), P5/RAM (zenodo.19669430)

LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology

Renan Souza, Timothy Poteet, Brian Etz, Daniel Rosendo, Amal Gueroudji, Woong Shin, Prasanna Balaprakash, Rafael Ferreira da Silva

机构 * Oak Ridge National Lab.（橡树岭国家实验室） ； Argonne National Lab.（阿贡国家实验室） 纠错

专题命中 工作流自动化 ：workflow(title,abstract)；agent(abstract)；分类 cs.AI

Comments Paper accepted in the proceedings of the Supercomputing Conference (SC). Cite it as Renan Souza, Timothy Poteet, Brian Etz, Daniel Rosendo, Amal Gueroudji, Woong Shin, Prasanna Balaprakash, and Rafael Ferreira da Silva. LLM Agents for Interactive Workflow Provenance: Reference Architecture and Evaluation Methodology. In WORKS at the ACM/IEEE International Conference on Supercomputing, 2025

MiniFed : Integrating LLM-based Agentic-Workflow for Simulating FOMC Meeting

Sungil Seok, Shuide Wen, Qiyuan Yang, Juan Feng, Wenming Yang

专题命中 工作流自动化 ：workflow(title)；agentic(title)

Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting

用于循证甲状腺超声诊断与报告的可审计智能体AI

Haifan Gong, Shiyu Chen, Bodong Wang, Yuqi Wang, Shijie Wang, Guoliang You, Xinyu Xiong, Haowei Wang, Mingzhi Mao, Dexing Kong, Qinghua Liu, Wei Lou, Fei Chen, Guanbin Li

机构 * School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院） ； School of Software Engineering, Sun Yat-sen University（中山大学软件工程学院） ； School of Mathematical Sciences, Zhejiang University（浙江大学数学科学学院） ； Perelman School of Medicine, University of Pennsylvania（宾夕法尼亚大学佩雷尔曼医学院） ； Zhujiang Hospital, Southern Medical University（南方医科大学珠江医院） ； College of Mathematical Medicine, Zhejiang Normal University（浙江师范大学数学医学院） 纠错

专题命中 工作流自动化 ：agentic(title,abstract)；workflow(abstract)；分类 cs.AI

AI总结 本文提出可审计的智能体AI系统ThyroidXAgent，基于多中心数据集开发，可协同完成甲状腺超声诊断多任务，提升分类准确率与报告一致性，缩短耗时，支持临床医生修正。

Comments Under review

Workflow Cards: Structured Summaries of Workflow Executions Using Provenance Data

工作流卡片：利用溯源数据生成工作流执行的结构化摘要

Nicola Giuseppe Marchioro, Gabriele Padovani, Amal Gueroudji, Rafael Ferreira da Silva, Wesley Brewer, Valentine Anantharaj, Sandro Fiore, Renan Souza

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

AI总结 本文提出工作流卡片，将工作流执行的溯源数据转化为可读的结构化摘要，填补了现有模型、数据卡片缺失执行级信息的空白，使LLM回答质量较传统查询提升近一倍。

Comments Accepted at eScience2026

OBLIVION: Workflow-Level Operational Skill Unlearning for Deployed Agents

OBLIVION：面向已部署智能体的工作流级操作技能遗忘

Zhengyang Shan, Xu Qian, Jiayun Xin, Kun Li, Yue Zhang, Minghui Xu

专题命中 工作流自动化 ：workflow(title,abstract)；agent(abstract)；分类 cs.AI

AI总结 研究大型语言模型智能体的技能撤销问题，提出OBLIVION框架，通过工作流建模、跨表面连贯擦除等技术降低技能复活风险，在基准与沙箱实验中有效减少攻击成功率与影响加权暴露。

Agentic AI for Clustering, Relationship Discovery, and Semantic Trading in Prediction Markets

语义交易：用于预测市场聚类和关系发现的代理AI

Agostino Capponi, Alfio Gliozzo, Brian Zhu

机构 * Columbia University（哥伦比亚大学） ； IBM Research（IBM研究院） 纠错

专题命中 工作流自动化 ：agentic(title,abstract)；workflow(abstract)；分类 cs.AI

AI总结 本文提出一种代理AI方法，通过自然语言处理将预测市场划分为主题组并发现市场间的关系，利用历史数据验证其预测准确性及交易策略收益。

GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks

GDPevo：在真实商业任务上评估智能体的自进化能力

Leijun Zhou, Zhihao Liu, Xiang Qu, Chenxu Liu, Yifei Liu, Yanke Yu, Jingzhe Xu, Xuejun Wu, Buyue Qian, Xi Chen, Yaowei Zheng, Junhao Hu

专题命中 工作流自动化 ：agent(title,abstract)；workflow(abstract)；分类 cs.AI

AI总结 本文提出GDPevo基准，通过规则杂交设计任务实现可归因评估，发现自进化可提升智能体测试准确率但仍远未达上限，相关资源已公开。