AI Agent - arXivDaily 专题

2112.00331 2021-12-02 cs.MM 67%

Mutltimodal AI Companion for Interactive Fairytale Co-creation

Ruiyang Liu, Predrag K. Nikolic

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

2105.07510 2021-10-12 cs.CL cs.AI cs.LG 67%

Doc2Dict: Information Extraction as Text Generation

Benjamin Townsend, Eamon Ito-Fisher, Lily Zhang, Madison May

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

2109.12845 2021-09-28 cs.CV cs.RO 67%

Bayesian deep learning of affordances from RGB images

Lorenzo Mur-Labadia, Ruben Martinez-Cantin

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

Comments 6 pages

2109.09923 2021-09-22 cs.CV cs.RO 67%

AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning

Hadi AlZayer, Hubert Lin, Kavita Bala

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

Comments Accepted to IROS 2021

2104.11489 2021-07-26 cs.RO cs.CV 67%

Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling with Real-World Data

Akshay Rangesh, Nachiket Deo, Ross Greer, Pujitha Gunaratne, Mohan M. Trivedi

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

2106.05756 2021-06-14 cs.CR 67%

Lifting The Grey Curtain: A First Look at the Ecosystem of CULPRITWARE

Zhuo Chen, Lei Wu, Jing Cheng, Yubo Hu, Yajin Zhou, Zhushou Tang, Yexuan Chen, Jinku Li, Kui Ren

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

Comments 13 pages, 10 figures

2102.10997 2021-02-23 cs.CR cs.PF 67%

Trust Computational Heuristic for Social Internet of Things: A Machine Learning-based Approach

Subhash Sagar, Adnan Mahmood, Quan Z. Sheng, Wei Emma Zhang

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

Comments 6 pages

2102.07574 2021-02-16 cs.SE cs.AI cs.LG 67%

Machine Learning Model Development from a Software Engineering Perspective: A Systematic Literature Review

Giuliano Lorenzoni, Paulo Alencar, Nathalia Nascimento, Donald Cowan

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

Comments 9 pages, 2 columns. Under review

2010.06030 2021-01-28 cs.CL cs.AI cs.LG cs.SD eess.AS 67%

Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling

Jiahui Yu, Wei Han, Anmol Gulati, Chung-Cheng Chiu, Bo Li, Tara N. Sainath, Yonghui Wu, Ruoming Pang

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

Comments Accepted in ICLR 2021

2012.08055 2021-01-07 cs.CV 67%

Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation

Feixiang Lu, Zongdai Liu, Hui Miao, Peng Wang, Liangjun Zhang, Ruigang Yang, Dinesh Manocha, Bin Zhou

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

2003.02746 2020-03-06 cs.RO 67%

Efficient Uncertainty-aware Decision-making for Automated Driving Using Guided Branching

Lu Zhang, Wenchao Ding, Jing Chen, Shaojie Shen

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

Comments Accepted by IEEE International Conference on Robotics and Automation (ICRA) 2020

2001.03801 2020-01-14 eess.IV cs.CV physics.med-ph 67%

Dynamic Coronary Roadmapping via Catheter Tip Tracking in X-ray Fluoroscopy with Deep Learning Based Bayesian Filtering

Hua Ma, Ihor Smal, Joost Daemen, Theo van Walsum

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

1906.10742 2019-12-24 cs.LG cs.AI cs.SE stat.ML 67%

Machine Learning Testing: Survey, Landscapes and Horizons

Jie M. Zhang, Mark Harman, Lei Ma, Yang Liu

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

1911.10823 2019-11-26 eess.SY cs.SY 67%

Optimal Model-Based Sensor Placement & Adaptive Monitoring Of An Oil Spill

Zak Hodgson, Inaki Esnaola, Bryn Jones

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

Comments Pre-print for IFACC 2020

1906.09384 2019-06-25 cs.AI cs.CL cs.LG 67%

A Bandit Approach to Posterior Dialog Orchestration Under a Budget

Sohini Upadhyay, Mayank Agarwal, Djallel Bounneffouf, Yasaman Khazaeni

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

Comments 2nd Conversational AI Workshop, NeurIPS 2018

1806.04095 2018-06-12 astro-ph.IM 67%

Sustaining the Montage Image Mosaic Engine Since 2002

G. Bruce Berriman, John C. Good

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

Comments 12 pages, 8 figures. Software and Cyberinfrastructure for Astronomy V (Conference 10707), SPIE SPIE Astronomical Telescopes + Instrumentation, Austin TX. June 10-15, 2018

1802.09335 2018-02-27 cs.CY 67%

An Integrated Pipeline Architecture for Modeling Urban Land Use, Travel Demand, and Traffic Assignment

Paul Waddell, Geoff Boeing, Max Gardner, Emily Porter

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

1402.3793 2015-12-07 physics.med-ph 67%

An anthropomorphic multimodality (CT/MRI) phantom prototype for end-to-end tests in radiation therapy

Raya R. Gallas, Nora Hünemohr, Armin Runz, Nina I. Niebuhr, Oliver Jäkel, Steffen Greilich

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

Comments 18 pages, 6 figures

Journal ref Zeitschrift fuer medizinische Physik, 2015, 25, 391-399

1102.3338 2011-02-17 nlin.AO 67%

Revisiting the Gaia Hypothesis: Maximum Entropy, Kauffman's 'Fourth Law' and Physiosemeiosis

Carsten Herrmann-Pillath

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

1008.1096 2010-08-09 physics.soc-ph cond-mat.stat-mech cs.MA 67%

The Naming Game in Social Networks: Community Formation and Consensus Engineering

Qiming Lu, G. Korniss, B. K. Szymanski

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

Comments The original publication is available at http://www.springerlink.com/content/70370l311m1u0ng3/

Journal ref Journal of Economic Interaction and Coordination 4, 221-235 (2009)

cs/0609041 2009-12-01 cs.MA 67%

Primitive operations for the construction and reorganization of minimally persistent formations

Julien M. Hendrickx, Baris Fidan, Changbin Yu, Brian D. O. Anderson, Vincent D. Blondel

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

Comments 26 pages, 31 .eps files for the figures

2603.05171 2026-06-17 cs.CL cs.AI 版本更新 66%

Guidelines for the Annotation and Visualization of Legal Argumentation Structures in Chinese Judicial Decisions

中国司法判决中法律论证结构的标注与可视化指南

Kun Chen, Xianglei Liao, Kaixue Fei, Yi Xing, Xinrui Li

机构 * Law School, Nanjing University（南京大学法学院）

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

AI总结提出一个系统化、可操作的标注框架，用于表示司法判决中的法律论证结构，支持大规模司法推理分析和法律论证挖掘。

Comments This Guideline has been developed through revision and refinement based on the first edition. The element label system has been adjusted, and the annotation granularity and annotation workflow have been further optimized

2602.17098 2026-02-20 q-fin.PM cs.AI cs.LG 66%

Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization

深度强化学习在最优投资组合分配中的应用：与均值-方差优化的比较研究

Srijan Sood, Kassiani Papasotiriou, Marius Vaiciulis, Tucker Balch

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

AI总结本文通过比较深度强化学习与均值-方差优化方法，探讨了在投资组合分配中的性能和效果。

Comments 9 pages, 6 figures. Published at the FinPlan'23 Workshop, the 33rd International Conference on Automated Planning and Scheduling (ICAPS 2023)

2404.19370 2024-05-01 cs.AI cs.LG 66%

Numeric Reward Machines

Kristina Levina, Nikolaos Pappas, Athanasios Karapantelakis, Aneta Vulgarakis Feljan, Jendrik Seipp

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

Comments ICAPS 2024; Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning

1301.2158 2018-10-09 cs.AI stat.ML 65%

Artificial Intelligence Framework for Simulating Clinical Decision-Making: A Markov Decision Process Approach

Casey C. Bennett, Kris Hauser

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

Comments Keywords: Markov Decision Process; Dynamic Decision Network; Multi-Agent System; Clinical Artificial Intelligence; Medical Decision Making; Chronic Illness; (2013) Artificial Intelligence in Medicine

Journal ref Artificial Intelligence in Medicine. 57(1): 9-19. (2013)

2608.19836 2026-08-21 cs.LG cs.AI cs.LO 新提交 62%

Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning

通过学习马尔可夫决策过程（MDP）实现自适应概率屏蔽用于安全强化学习

Astrid Horn Brorholt, Maris F. L. Galesloot, Nils Jansen, Kim Guldstrand Larsen, Christian Schilling

机构 * Aalborg University（奥尔堡大学）； Radboud University（拉德堡德大学）； Ruhr University Bochum（波鸿鲁尔大学）

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

AI总结本文针对已知MDP转移图但转移概率未知的场景，提出将概率屏蔽与在线模型学习结合的自适应方法，通过实验验证其在安全强化学习中的有效性。

Comments 19 pages, 3 figures, 3 tables. To be published in the proceedings of RV 2026

2608.18149 2026-08-20 cs.AR cs.AI cs.DC cs.LG cs.PF 新提交 62%

TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving

TokenPowerSandbox：面向能源感知大语言模型服务的证据门控CPU优先筛选

Chenxu Niu

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

AI总结 TokenPowerSandbox是面向能源感知LLM服务的证据门控CPU优先筛选工作流，结合CPU投影器、GPU探测等技术，在H100上评估Qwen2.5-7B-Instruct，验证了能源与延迟预测的关联及弃权门控的必要性。

2608.14640 2026-08-18 cs.LG cond-mat.mtrl-sci cs.AI 新提交 62%

BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materials

BDIP-Net：用于双层材料性能预测的双交互图学习方法

An Vuong, Chen Zhao, Jin Hu, Shui-Qing Yu, Xintao Wu

机构 * University of Arkansas（阿肯色大学）； Baylor University（贝勒大学）

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

AI总结本研究提出基于MatterSim-D3的结构优化工作流与BDIP-Net图神经网络，实现了双层材料的低成本高效构建与性能预测，且BDIP-Net性能优于现有相关方法。

2605.27599 2026-08-18 cs.LG cs.AI cs.AR cs.DC cs.PF 版本更新 62%

The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution

能源盲点：NVIDIA 旗舰边缘 AI 硬件无法支持进程级能源归因

Deepak Panigrahy, Aakash Tyagi

机构 * Independent Researcher（独立研究者）； Texas A&M University（德克萨斯农工大学）

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

AI总结本文审计了 ASUS Ascent GX10 (GB10 SoC) 平台的能源可观测性，发现其缺乏 CPU 能源计数器等关键接口，导致无法像 x86 的 RAPL 那样进行进程级能源归因，并提出通过外部直流计量和 GPU 减法进行校准的临时方案，呼吁将能源可观测性作为硬件的一等要求。

Comments 5 pages, 0 figures. Accepted at the 2nd International Workshop on Low Carbon Computing (LOCO 2026), Lancaster University, United Kingdom, 10-11 September 2026. Part of the LOCO 2026 proceedings, arXiv:2608.02072

2607.28008 2026-08-17 cs.CL cs.AI 版本更新 62%

RepBench: Compiling Benchmarks into Capability Representations for Large Language Models

RepBench：将基准编译为大语言模型的能力表征

Yanshi Li, Xueru Bai, Shuman Liu, Long Zhang

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

AI总结 RepBench构建多基准支撑的大语言模型能力表征探测数据层，揭示读出方式与聚合准则对评估的重要性，相关资源以闭环工作流形式发布。

Comments 22 pages, 8 figures, with appendices. Yanshi Li and Xueru Bai contributed equally

1. 工作流自动化 10469 篇

Mutltimodal AI Companion for Interactive Fairytale Co-creation

Doc2Dict: Information Extraction as Text Generation

Bayesian deep learning of affordances from RGB images

AutoPhoto: Aesthetic Photo Capture using Reinforcement Learning

Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling with Real-World Data

Lifting The Grey Curtain: A First Look at the Ecosystem of CULPRITWARE

Trust Computational Heuristic for Social Internet of Things: A Machine Learning-based Approach

Machine Learning Model Development from a Software Engineering Perspective: A Systematic Literature Review

Dual-mode ASR: Unify and Improve Streaming ASR with Full-context Modeling

Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation

Efficient Uncertainty-aware Decision-making for Automated Driving Using Guided Branching

Dynamic Coronary Roadmapping via Catheter Tip Tracking in X-ray Fluoroscopy with Deep Learning Based Bayesian Filtering

Machine Learning Testing: Survey, Landscapes and Horizons

Optimal Model-Based Sensor Placement & Adaptive Monitoring Of An Oil Spill

A Bandit Approach to Posterior Dialog Orchestration Under a Budget

Sustaining the Montage Image Mosaic Engine Since 2002

An Integrated Pipeline Architecture for Modeling Urban Land Use, Travel Demand, and Traffic Assignment

An anthropomorphic multimodality (CT/MRI) phantom prototype for end-to-end tests in radiation therapy

Revisiting the Gaia Hypothesis: Maximum Entropy, Kauffman's 'Fourth Law' and Physiosemeiosis

The Naming Game in Social Networks: Community Formation and Consensus Engineering

Primitive operations for the construction and reorganization of minimally persistent formations

Guidelines for the Annotation and Visualization of Legal Argumentation Structures in Chinese Judicial Decisions

Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization

Numeric Reward Machines

Artificial Intelligence Framework for Simulating Clinical Decision-Making: A Markov Decision Process Approach

Adaptive Probabilistic Shielding by Learning MDPs for Safe Reinforcement Learning

TokenPowerSandbox: Evidence-Gated CPU-First Screening for Energy-Aware LLM Serving

BDIP-Net: Dual-Interaction Graph Learning for Property Prediction of Bilayer Materials

The Energy Blind Spot: NVIDIA's Flagship Edge AI Hardware Cannot Support Process-Level Energy Attribution

RepBench: Compiling Benchmarks into Capability Representations for Large Language Models