AI Agent - arXivDaily 专题

1709.08607 2017-12-06 physics.data-an cs.AI cs.LG hep-ex 62%

Towards automation of data quality system for CERN CMS experiment

Maxim Borisyak, Fedor Ratnikov, Denis Derkach, Andrey Ustyuzhanin

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

1711.09357 2017-11-28 cs.CL cs.AI 62%

Generative Adversarial Network for Abstractive Text Summarization

Linqing Liu, Yao Lu, Min Yang, Qiang Qu, Jia Zhu, Hongyan Li

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

Comments AAAI 2018 abstract, Supplemental material: http://likicode.com/textsum/

1708.08611 2017-09-05 cs.LO cs.AI cs.LG 62%

Safe Reinforcement Learning via Shielding

Mohammed Alshiekh, Roderick Bloem, Ruediger Ehlers, Bettina Könighofer, Scott Niekum, Ufuk Topcu

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

1611.01843 2017-08-21 stat.ML cs.AI cs.CV cs.LG cs.NE physics.soc-ph 62%

Learning to Perform Physics Experiments via Deep Reinforcement Learning

Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas

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

1703.09310 2017-08-01 cs.LG cs.AI cs.RO stat.ML 62%

Adaptive Simulation-based Training of AI Decision-makers using Bayesian Optimization

Brett W. Israelsen, Nisar Ahmed, Kenneth Center, Roderick Green, Winston Bennett

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

Comments submitted to JAIS for review

1612.03981 2016-12-14 stat.ML cs.AI cs.LG cs.RO 62%

Hybrid Repeat/Multi-point Sampling for Highly Volatile Objective Functions

Brett Israelsen, Nisar Ahmed

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

Journal ref BayesOpt Workshop, NIPS 2016

1605.00164 2016-08-09 cs.CV cs.AI cs.LG cs.RO 62%

Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion

Dinesh Jayaraman, Kristen Grauman

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

Comments A preliminary version of the material in this document was filed as University of Texas technical report no. UT AI15-06, December, 2015, at: http://apps.cs.utexas.edu/tech_reports/reports/ai/AI-2214.pdf, ECCV 2016

1602.08017 2016-05-31 cs.AI cs.LG stat.ML 62%

Meta-learning within Projective Simulation

Adi Makmal, Alexey A. Melnikov, Vedran Dunjko, Hans J. Briegel

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

Comments 14 pages, 12 figures

Journal ref IEEE Access 4, 2110-2122 (2016)

1510.00878 2016-01-12 cs.LG cs.AI stat.ML 62%

Client Profiling for an Anti-Money Laundering System

Claudio Alexandre, João Balsa

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

Comments 7 pages, 15 figures, 3 tables

1412.0436 2015-09-08 cs.MS cs.LG cs.SE stat.CO 62%

An Infra-Structure for Performance Estimation and Experimental Comparison of Predictive Models in R

Luis Torgo

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

Comments Updated to version 1.0.2 of the R package. Added a small section on package installation. Made explicit the reference to the R package version number within the document

1107.1322 2015-03-19 cs.AI cs.IR cs.LG 62%

Text Classification: A Sequential Reading Approach

Gabriel Dulac-Arnold, Ludovic Denoyer, Patrick Gallinari

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

Comments ECIR2011

Journal ref Lecture Notes in Computer Science, 2011, Volume 6611/2011, 411-423

1308.3513 2013-08-19 cs.LG cs.AI 62%

Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations

Finale Doshi-Velez, George Konidaris

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

1210.1317 2012-10-05 cs.LG cs.AI 62%

Learning Heterogeneous Similarity Measures for Hybrid-Recommendations in Meta-Mining

Phong Nguyen, Jun Wang, Melanie Hilario, Alexandros Kalousis

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

1206.6484 2012-07-02 cs.LG cs.AI stat.ML 62%

Apprenticeship Learning for Model Parameters of Partially Observable Environments

Takaki Makino, Johane Takeuchi

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

Comments Appears in Proceedings of the 29th International Conference on Machine Learning (ICML 2012)

1109.0621 2011-09-06 cs.AI cs.SE 62%

Visual Inference Specification Methods for Modularized Rulebases. Overview and Integration Proposal

Krzysztof Kluza, Grzegorz J. Nalepa, Łukasz Łysik

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

Comments from the KESE6 workshop at the 33rd German AI Conference KI-2010 in Karlsruhe (see: http://ai.ia.agh.edu.pl/wiki/kese:kese6)

2604.18085 2026-04-21 cs.LG 61%

Predicting LLM Compression Degradation from Spectral Statistics

从谱统计预测大语言模型压缩退化

Mingxue Xu

机构 * Department of Electrical and Electronic Engineering, Imperial College London（帝国理工学院伦敦分校电子与电气工程系）

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

AI总结本文通过分析四种低秩压缩方法，发现稳定秩和信息密度主导性能退化，提出γ·ρ_s交互项作为准确度退化的预测指标，实现了高相关性验证。

Comments Profoundly assisted by agentic AI

2501.06873 2026-02-25 econ.GN cs.CL cs.IR cs.SI q-fin.EC stat.ME 61%

Causal Claims in Economics

经济学中的因果主张

Prashant Garg, Thiemo Fetzer

机构 * CEPR Paris Symposium（CEPR巴黎研讨会）； Metascience（元科学）； NetSciSci（网络科学）； EAYE ； Groningen ； AYEW ； ZBW ； MPWZ-CEPR Text-As-Data（MPWZ-CEPR文本作为数据）； PolMeth ； Leibniz Open Science（莱布尼茨开放科学）； Causal Data Science Meeting（因果数据科学会议）

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

AI总结本研究通过构建证据注释的主张图，分析经济学论文中因果关系的演变及其对学术影响力的影响。

Comments Data, code, prompts, and workflow documentation are publicly available at our GitHub repository: https://github.com/prashgarg/CausalClaimsInEconomics

2509.16599 2025-10-28 cs.CL cs.IR stat.AP stat.ME 61%

Computational-Assisted Systematic Review and Meta-Analysis (CASMA): Effect of a Subclass of GnRH-a on Endometriosis Recurrence

Sandro Tsang

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

Comments 15 pages, 12 figures and 4 tables. This work describes an information retrieval-driven workflow for medical evidence synthesis, with an application to endometriosis recurrence. The method can be generalized to other systematic reviews. The preregistered protocol is available: https://doi.org/10.17605/OSF.IO/R2DFA

2510.17184 2025-10-21 cs.SE 61%

OLIVAW: ACIMOV's GitHub robot assisting agile collaborative ontology development

Nicolas Robert, Fabien Gandon, Maxime Lefrançois

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

Journal ref 24th IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology, Nov 2025, London, United Kingdom

2406.19708 2024-09-26 cs.NE cs.AI cs.CE q-bio.NC 61%

A Differentiable Approach to Multi-scale Brain Modeling

Chaoming Wang, Muyang Lyu, Tianqiu Zhang, Sichao He, Si Wu

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

Comments 2nd Differentiable Almost Everything Workshop at ICML 2024. https://github.com/chaoming0625/differentiable-brain-modeling-workflow

2401.06801 2024-02-20 cs.AI 61%

Graph-of-Thought: Utilizing Large Language Models to Solve Complex and Dynamic Business Problems

Ye Li

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

Comments Keywords: Graph-of-Thought (GoT), Workflow Automation, Large Language Models (LLMs), Task Execution, Data-Driven Decision Making, Complexity Management

2103.14065 2021-03-29 physics.chem-ph cond-mat.mtrl-sci cs.LG 61%

Quantitative Prediction on the Enantioselectivity of Multiple Chiral Iodoarene Scaffolds Based on Whole Geometry

Prema Dhorma Lama, Surendra Kumar, Kang Kim, Sangjin Ahn, Mi-hyun Kim

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

Comments 73 pages, 27 figures, It described the enantioselective transformational potency of catalysts across reactions and introduced a predictive workflow to extend the reaction scope of chiral catalysts based on whole molecular geometry. Though the work is technically sound & well-presented, it is too focused on the enantioselective prediction of iodoarenes with favorable statistical performance

1910.04102 2020-03-03 stat.ML cs.LG math.ST stat.ME stat.TH 61%

Validated Variational Inference via Practical Posterior Error Bounds

Jonathan H. Huggins, Mikołaj Kasprzak, Trevor Campbell, Tamara Broderick

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

Comments A python package for carrying out our validated variational inference workflow -- including doing black-box variational inference and computing the bounds we develop in this paper -- is available at https://github.com/jhuggins/viabel. The same repository also contains code for reproducing all of our experiments

Journal ref Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics (AISTATS) 2020, Palermo, Italy. PMLR: Volume 108

1404.7509 2014-05-01 cs.SE 61%

On Cloud-Based Engineering of Dependable Systems

Sami Alajrami

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

Comments EDCC-2014, Student-Forum, Cloud Computing, Cloud Workflow Systems, Dependable, Systems, Software Engineering

2208.00096 2022-08-02 cs.RO cs.MA 60%

Perspectives on the System-level Design of a Safe Autonomous Driving Stack

Majd Hawasly, Jonathan Sadeghi, Morris Antonello, Stefano V. Albrecht, John Redford, Subramanian Ramamoorthy

专题命中工作流自动化：planning(abstract)；agent(comments)；multi-agent(comments)

Comments AI Communications special issue on Multi-agent Systems Research in the UK

2608.20963 2026-08-24 cs.CR cs.AI 新提交 57%

Vibe Coding and Web Application Security: A Twin-Prompt Study

Vibe编码与Web应用安全：一项双提示研究

Darko Andročec

专题命中工作流自动化：agentic(abstract)；分类 cs.AI

AI总结本研究通过双提示实验对比发现，明确要求安全最佳实践的Web应用生成结果，其安全问题数量更少且无高危问题，是关于LLM生成Web应用安全的初步研究。

Comments Accepted for presentation at the 37th Central European Conference on Information and Intelligent Systems (CECIIS 2026), September 16-18, 2026, Varazdin, Croatia. Author's accepted manuscript

2608.20904 2026-08-24 cs.RO cs.DB cs.SE 新提交 57%

Scalable Distributed Simulation-Based Testing for Automated Driving Systems

面向自动驾驶系统的可扩展分布式基于仿真的测试

Christian Geller, Benedikt Haas, Lutz Eckstein

机构 * RWTH Aachen University（亚琛工业大学）； Institute for Automotive Engineering (ika)（汽车工程研究所（ika））

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

AI总结本文提出一种DevOps驱动的端到端框架，在轻量级Kubernetes集群上自动化CARLA场景测试的构建与分布式执行，200个场景测试的端到端时间较基线提速超8倍，为ADS可扩展仿真测试提供支撑。

Comments 14 pages; Accepted to be published as part of the 17. Uni-DAS e.V. Workshop "Fahrerassistenz und automatisiertes Fahren", September 29-30, 2026

2608.20845 2026-08-24 cs.AI cs.DB cs.IR 新提交 57%

RAG Deserves an Index: Why Ingest-Time Compilation Beats Query-Time Interpretation

检索增强生成（RAG）值得一个索引：为什么摄入时编译优于查询时解释

Kyle Wild, Yusuke Takahashi, Asako Uraki

机构 * Endgame Labs, Inc.（终局实验室公司）； Asia AI Institute（亚洲人工智能研究院）； Musashino University（武藏野大学）； Faculty of Data Science, Musashino University（武藏野大学数据科学学院）； AIx, Inc.（AIx公司）

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

AI总结该研究提出摄入时语义编译（ISC）范式，将语料编译为可查询数据库对象，实验显示其检索效果优于传统RAG方法，增量更新成本更低，为RAG提供了索引化解决方案。

Comments Position paper. 6 pages, 2 figures, 2 tables

2608.20580 2026-08-24 cs.CR cs.LG 新提交 57%

Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning

面向联邦学习的结合互补格基安全聚合的密钥化来源水印

Xinyun Liu, Zhi Lu, Yu Chen, Ronghua Xu

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

AI总结本研究针对联邦学习面临的多级攻击问题，提出结合密钥化来源水印与格基安全聚合的FL框架，经实验验证其在复合攻击下具备互补保护能力，且为端到端可信FL提供了联合评估方案。

2608.20539 2026-08-24 cs.CY cs.AI cs.HC 新提交 57%

ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations

ExploraTwin：一个用于数字孪生模拟的非营利研究平台

Naveen Venkatanarayanan, Yuchen Qiu, Tianyi Peng, George Gui, Olivier Toubia

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

AI总结本研究推出非营利数字孪生模拟平台ExploraTwin，支持调查与小组模式，开发了标准化数据格式CroissantTwin，复现数据集实验验证其调查执行保真度达99.6%，降低了相关研究的测试部署门槛。

Comments 44 pages (32-page manuscript plus web appendix), 8 figures. Platform: this https URL (https://exploratwin.org)

1. 工作流自动化 10492 篇

Towards automation of data quality system for CERN CMS experiment

Generative Adversarial Network for Abstractive Text Summarization

Safe Reinforcement Learning via Shielding

Learning to Perform Physics Experiments via Deep Reinforcement Learning

Adaptive Simulation-based Training of AI Decision-makers using Bayesian Optimization

Hybrid Repeat/Multi-point Sampling for Highly Volatile Objective Functions

Look-ahead before you leap: end-to-end active recognition by forecasting the effect of motion

Meta-learning within Projective Simulation

Client Profiling for an Anti-Money Laundering System

An Infra-Structure for Performance Estimation and Experimental Comparison of Predictive Models in R

Text Classification: A Sequential Reading Approach

Hidden Parameter Markov Decision Processes: A Semiparametric Regression Approach for Discovering Latent Task Parametrizations

Learning Heterogeneous Similarity Measures for Hybrid-Recommendations in Meta-Mining

Apprenticeship Learning for Model Parameters of Partially Observable Environments

Visual Inference Specification Methods for Modularized Rulebases. Overview and Integration Proposal

Predicting LLM Compression Degradation from Spectral Statistics

Causal Claims in Economics

Computational-Assisted Systematic Review and Meta-Analysis (CASMA): Effect of a Subclass of GnRH-a on Endometriosis Recurrence

OLIVAW: ACIMOV's GitHub robot assisting agile collaborative ontology development

A Differentiable Approach to Multi-scale Brain Modeling

Graph-of-Thought: Utilizing Large Language Models to Solve Complex and Dynamic Business Problems

Quantitative Prediction on the Enantioselectivity of Multiple Chiral Iodoarene Scaffolds Based on Whole Geometry

Validated Variational Inference via Practical Posterior Error Bounds

On Cloud-Based Engineering of Dependable Systems

Perspectives on the System-level Design of a Safe Autonomous Driving Stack

Vibe Coding and Web Application Security: A Twin-Prompt Study

Scalable Distributed Simulation-Based Testing for Automated Driving Systems

RAG Deserves an Index: Why Ingest-Time Compilation Beats Query-Time Interpretation

Keyed Provenance Watermarking with Complementary Lattice-Based Secure Aggregation for Federated Learning

ExploraTwin, a Non-Profit Research Platform for Digital Twin Simulations