AI Agent - arXivDaily 专题

2207.09109 2022-11-08 cs.LG cs.DC 70%

Active-Learning-as-a-Service: An Automatic and Efficient MLOps System for Data-Centric AI

Yizheng Huang, Huaizheng Zhang, Yuanming Li, Chiew Tong Lau, Yang You

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

Comments 13 pages, 5 figures

2207.06105 2022-10-14 cs.AI 70%

GriddlyJS: A Web IDE for Reinforcement Learning

Christopher Bamford, Minqi Jiang, Mikayel Samvelyan, Tim Rocktäschel

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

2209.08200 2022-09-22 cs.LG 70%

Deep Labeling of fMRI Brain Networks Using Cloud Based Processing

Sejal Ghate, Alberto Santamaria-Pang, Ivan Tarapov, Haris I Sair, Craig K Jones

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

Comments International Symposium on Visual Computing

2209.03433 2022-09-09 cs.LG 70%

Responsibility: An Example-based Explainable AI approach via Training Process Inspection

Faraz Khadivpour, Arghasree Banerjee, Matthew Guzdial

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

2011.10896 2022-07-08 cs.DC cs.CL cs.PF 70%

HALO 1.0: A Hardware-agnostic Accelerator Orchestration Framework for Enabling Hardware-agnostic Programming with True Performance Portability for Heterogeneous HPC

Michael Riera, Erfan Bank Tavakoli, Masudul Hassan Quraishi, Fengbo Ren

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

Comments 37 pages

2206.00636 2022-06-02 cs.AI cs.HC cs.RO 70%

A modular architecture for creating multimodal agents

Thomas Baier, Selene Baez Santamaria, Piek Vossen

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

2111.08102 2022-02-25 cs.AI cs.GT 70%

The Partially Observable History Process

Dustin Morrill, Amy R. Greenwald, Michael Bowling

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

Comments 8 pages, 2 figures

Journal ref AAAI-22 Workshop on Reinforcement Learning and Games, February 28, 2022

2109.06740 2021-09-15 cs.AI 70%

Deceptive Decision-Making Under Uncertainty

Yagiz Savas, Christos K. Verginis, Ufuk Topcu

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

2102.02441 2021-09-06 cs.AI cs.MA 70%

Persistent Rule-based Interactive Reinforcement Learning

Adam Bignold, Francisco Cruz, Richard Dazeley, Peter Vamplew, Cameron Foale

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

Comments 24 pages, 7 figures

2108.05595 2021-08-13 cs.LG 70%

Reinforcement Learning Approach to Active Learning for Image Classification

Thorben Werner

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

Comments Master Thesis

2104.06106 2021-04-14 cs.AI 70%

Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution

Takumi Tanabe, Kazuto Fukuchi, Jun Sakuma, Youhei Akimoto

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

Comments The Genetic and Evolutionary Computation Conference 2021 (GECCO '21)

2102.02488 2021-02-05 stat.ML cs.LG 70%

From a Point Cloud to a Simulation Model: Bayesian Segmentation and Entropy based Uncertainty Estimation for 3D Modelling

Christina Petschnigg, Markus Spitzner, Lucas Weitzendorf, Jürgen Pilz

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

Comments Submitted to MDPI Entropy for Review

1907.00824 2021-01-29 cs.HC cs.LG cs.SD eess.AS 70%

Designing Deep Reinforcement Learning for Human Parameter Exploration

Hugo Scurto, Bavo Van Kerrebroeck, Baptiste Caramiaux, Frédéric Bevilacqua

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

Comments Author's version of the work. The definitive Version of Record was published in ACM Transactions on Computer-Human Interaction (TOCHI)

Journal ref ACM Trans. Comput.-Hum. Interact. 28, 1, Article 1 (January 2021), 35 pages (2021)

2003.03190 2020-12-17 stat.ML cs.LG physics.chem-ph 70%

A Bayesian algorithm for retrosynthesis

Zhongliang Guo, Stephen Wu, Mitsuru Ohno, Ryo Yoshida

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

Journal ref J. Chem. Inf. Model. 60 (2020) 4474-4486

2010.07529 2020-10-20 cs.SE 70%

Introducing Artificial Intelligence Agents to the Empirical Measurement of Design Properties for Aspect Oriented Software Development

Senthil Velan S

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

2010.01676 2020-10-06 cs.AI 70%

Explainability via Responsibility

Faraz Khadivpour, Matthew Guzdial

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

Comments 8 pages, 4 figures

Journal ref Proceedings of the 2020 Experiment AI in Games Workshop

2009.00249 2020-09-02 cs.HC cs.AI 70%

PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning

Tan Tang, Renzhong Li, Xinke Wu, Shuhan Liu, Johannes Knittel, Steffen Koch, Thomas Ertl, Lingyun Yu, Peiran Ren, Yingcai Wu

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

Comments to be published in IEEE VIS InfoVis 2020

2007.08001 2020-07-17 cs.DC cs.LG 70%

Computation Offloading in Beyond 5G Networks: A Distributed Learning Framework and Applications

Xianfu Chen, Celimuge Wu, Zhi Liu, Ning Zhang, Yusheng Ji

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

2003.03001 2020-03-09 cs.SE 70%

The Cost and Benefits of Static Analysis During Development

William R. Nichols

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

Comments 10 pages plus feferences

1809.04232 2018-09-13 cs.AI 70%

Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process

Akifumi Wachi, Hiroshi Kajino, Asim Munawar

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

Comments 12 pages, 7 figures

1707.04775 2017-08-15 cs.AI 70%

AI Challenges in Human-Robot Cognitive Teaming

Tathagata Chakraborti, Subbarao Kambhampati, Matthias Scheutz, Yu Zhang

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

1609.02846 2016-09-12 cs.CL 70%

Dialogue manager domain adaptation using Gaussian process reinforcement learning

Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona, Pei-Hao Su, Stefan Ultes, David Vandyke, Tsung-Hsien Wen, Steve Young

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

Comments accepted for publication in Computer Speech and Language

1607.06324 2016-08-05 cs.SE 70%

Modeling Software Development Methodologies: A Logic Based Approach

Farzad Mahdikhani, Mohammad Reza Abbasifard

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

2412.02410 2025-08-05 cs.SE cs.AI 68%

AutoPLC: Generating Vendor-Aware Structured Text for Programmable Logic Controllers

Donghao Yang, Aolang Wu, Tianyi Zhang, Li Zhang, Fang Liu, Xiaoli Lian, Yuming Ren, Jiaji Tian, Xiaoyin Che

机构 * Beihang University, China（北京航空航天大学）； Siemens AG（西门子股份公司）

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

Comments 12 pages, 3 figures. Replaces "A Multi-Agent Framework for Extensible Structured Text Generation in PLCs" with an updated AutoPLC framework and new experiments

2608.23336 2026-08-25 cs.CV 新提交 67%

Can Coding Agents Build Robust Baselines? A Skill-Based Approach for Automating the Medical Imaging Model-Development Pipeline

编码智能体能构建鲁棒基线吗？一种基于技能的医学影像模型开发流水线自动化方法

Eugenia Moris, José Ignacio Orlando

机构 * Arionkoder LLC（阿里昂科德有限责任公司）； Yatiris（亚蒂里斯）； UNICEN-CONICET（国立中央大学-阿根廷国家科学技术研究委员会）

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

AI总结该研究提出一种结合文献引导推理等的智能体式AI科学家工作流，可自动化医学影像模型开发流水线，在四个公开基准上取得竞争力结果，大幅降低相关工程工作量。

Comments MICCAI 2026 Workshop AgenticMed

2512.17445 2026-08-25 cs.CV 版本更新 67%

LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents

LangDriveCTRL: 通过多模态代理实现自然语言可控的驾驶场景编辑

Yun He, Francesco Pittaluga, Ziyu Jiang, Matthias Zwicker, Manmohan Chandraker, Zaid Tasneem

机构 * University of Maryland, College Park（马里兰大学帕克分校）； NEC Labs America（NEC美国实验室）； UC San Diego（加州大学圣迭戈分校）

专题命中工作流自动化：agent(abstract)；agentic(abstract)

AI总结 LangDriveCTRL通过多模态代理实现驾驶视频的自然语言可控编辑，生成多样化的交通场景，提升真实感和交通场景的真实性。

Comments Accepted by ECCV 2026. Project Page: https://yunhe24.github.io/langdrivectrl/

2602.18492 2026-08-25 cs.DB cs.AI cs.CL cs.SE 版本更新 67%

Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries

Vibe Coding on Trial: Unanimous LLM Juries的运行特性

Muhammad Aziz Ullah, Abdul Serwadda

机构 * Texas Tech University（德克萨斯农工大学）

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

AI总结本文研究了使用多数LLM陪审团在代码审查中减少假接受的同时保持高准确率的方法，通过基准测试和实验验证了委员会大小和组成对安全性的影响。

Comments Submitted to IEEE International Conference on Semantic Computing 2026

2608.20546 2026-08-24 cs.RO 新提交 67%

Koala Gripper: Co-designing Robotic Grippers and Data-Capture Devices for Scaling Dexterous Manipulation Learning

考拉夹持器：为扩展灵巧操作学习而协同设计机器人夹持器与数据采集装置

Amar Hajj-Ahmad, Zubin Kremer Guha, Tim Fofonoff, Zhi Ern Teoh, Ciarán T. O'Neill, Ben Thacher, Igor Fala, Vidullan Surendran, Murphy Wonsick, Peter Whitney, David Watkins

专题命中工作流自动化：tool use(abstract)；workflow(abstract)

AI总结本文提出协同设计框架，开发Koala Gripper系统，该系统兼具数据采集与机器人夹持器功能，可提升灵巧操作能力，经端到端管道验证能支持演示学习，助力扩展操作数据集规模。

Comments Paper website: http://koalagripper.rai-inst.com Paper video: http://www.youtube.com/watch?v=ZoygFCWAVhg

2608.18745 2026-08-20 hep-ex physics.comp-ph 新提交 67%

FAST-HEP: Compiling Declarative Analysis Workflows for High-Energy Physics and Beyond

FAST-HEP：为高能物理及其他领域编译声明式分析工作流

Luke Kreczko

专题命中工作流自动化：planning(abstract)；workflow(abstract)

AI总结 FAST-HEP的Flow引擎将声明式工作流语言、编译器与运行时结合，编译生成与后端无关的执行计划，支持模块化替换与溯源记录，为高能物理及其他领域提供透明可重复的工作流基础。

2608.14869 2026-08-18 cs.HC 新提交 67%

RaivenTracks: Branching Provenance for Conversational Visualization Workflows

RaivenTracks：面向对话式可视化工作流的分支溯源系统

Ella Hugie, Alexandra Irger, Grace Guo, Kenneth Moreland, David Pugmire, Scott Klasky, Hanspeter Pfister

专题命中工作流自动化：AI agent(abstract)；workflow(abstract)

AI总结 RaivenTracks是Raiven可视化管道的工作流感知扩展，通过两级状态管理架构实现可分支的版本树与细粒度撤销/重做，试点研究显示其支持可视化工作流的分支与恢复，为AI驱动科学工作流的溯源监督提供了新方向。

Comments *Ella Hugie and Alexandra Irger are co-first authors

1. 工作流自动化 10514 篇

Active-Learning-as-a-Service: An Automatic and Efficient MLOps System for Data-Centric AI

GriddlyJS: A Web IDE for Reinforcement Learning

Deep Labeling of fMRI Brain Networks Using Cloud Based Processing

Responsibility: An Example-based Explainable AI approach via Training Process Inspection

HALO 1.0: A Hardware-agnostic Accelerator Orchestration Framework for Enabling Hardware-agnostic Programming with True Performance Portability for Heterogeneous HPC

A modular architecture for creating multimodal agents

The Partially Observable History Process

Deceptive Decision-Making Under Uncertainty

Persistent Rule-based Interactive Reinforcement Learning

Reinforcement Learning Approach to Active Learning for Image Classification

Level Generation for Angry Birds with Sequential VAE and Latent Variable Evolution

From a Point Cloud to a Simulation Model: Bayesian Segmentation and Entropy based Uncertainty Estimation for 3D Modelling

Designing Deep Reinforcement Learning for Human Parameter Exploration

A Bayesian algorithm for retrosynthesis

Introducing Artificial Intelligence Agents to the Empirical Measurement of Design Properties for Aspect Oriented Software Development

Explainability via Responsibility

PlotThread: Creating Expressive Storyline Visualizations using Reinforcement Learning

Computation Offloading in Beyond 5G Networks: A Distributed Learning Framework and Applications

The Cost and Benefits of Static Analysis During Development

Safe Exploration in Markov Decision Processes with Time-Variant Safety using Spatio-Temporal Gaussian Process

AI Challenges in Human-Robot Cognitive Teaming

Dialogue manager domain adaptation using Gaussian process reinforcement learning

Modeling Software Development Methodologies: A Logic Based Approach

AutoPLC: Generating Vendor-Aware Structured Text for Programmable Logic Controllers

Can Coding Agents Build Robust Baselines? A Skill-Based Approach for Automating the Medical Imaging Model-Development Pipeline

LangDriveCTRL: Natural Language Controllable Driving Scene Editing with Multi-modal Agents

Vibe Coding on Trial: Operating Characteristics of Unanimous LLM Juries

Koala Gripper: Co-designing Robotic Grippers and Data-Capture Devices for Scaling Dexterous Manipulation Learning

FAST-HEP: Compiling Declarative Analysis Workflows for High-Energy Physics and Beyond

RaivenTracks: Branching Provenance for Conversational Visualization Workflows