AI Agent - arXivDaily 专题

2411.00890 2024-11-05 cs.CL cs.AI stat.ML 62%

Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research

Marcello Carammia, Stefano Maria Iacus, Giuseppe Porro

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

2311.18760 2024-11-04 cs.CL cs.AI 62%

TaskBench: Benchmarking Large Language Models for Task Automation

Yongliang Shen, Kaitao Song, Xu Tan, Wenqi Zhang, Kan Ren, Siyu Yuan, Weiming Lu, Dongsheng Li, Yueting Zhuang

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

Comments Accepted to NeurIPS 2024

2410.23483 2024-11-01 cs.LG cs.AI cs.CR cs.CV cs.MA 62%

Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System

Julian Collado, Kevin Stangl

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

Comments 11 pages, 2 figures

2410.22812 2024-10-31 cs.LG cs.AI cs.ET math.ST stat.ML stat.TH 62%

Universality of the $π^2/6$ Pathway in Avoiding Model Collapse

Apratim Dey, David Donoho

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

Comments 30 pages

2410.21317 2024-10-30 cond-mat.mtrl-sci cs.AI cs.CL 62%

MatExpert: Decomposing Materials Discovery by Mimicking Human Experts

Qianggang Ding, Santiago Miret, Bang Liu

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

2403.19060 2024-10-27 cs.RO cs.AI cs.HC cs.LG 62%

Towards Human-Centered Construction Robotics: A Reinforcement Learning-Driven Companion Robot for Contextually Assisting Carpentry Workers

Yuning Wu, Jiaying Wei, Jean Oh, Daniel Cardoso Llach

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

Comments 8 pages, 9 figures. This work has been submitted to the IEEE for possible publication

2410.17209 2024-10-23 cs.SD cs.CL cs.LG eess.AS 62%

Audio-to-Score Conversion Model Based on Whisper methodology

Hongyao Zhang, Bohang Sun

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

Comments 5 pages, 7 figures

2410.10852 2024-10-16 cs.CL cs.AI 62%

SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance

Connor Walker, Callum Rothon, Koorosh Aslansefat, Yiannis Papadopoulos, Nina Dethlefs

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

2410.10315 2024-10-16 cs.CL cs.AI 62%

EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations

Zhangchi Feng, Dongdong Kuang, Zhongyuan Wang, Zhijie Nie, Yaowei Zheng, Richong Zhang

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

Comments 10 pages, 2 figures

2401.03462 2024-10-14 cs.CL cs.AI 62%

Long Context Compression with Activation Beacon

Peitian Zhang, Zheng Liu, Shitao Xiao, Ninglu Shao, Qiwei Ye, Zhicheng Dou

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

Comments Newer version of Activation Beacon

2410.07706 2024-10-11 cs.CL cs.AI 62%

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories

Yifan Song, Weimin Xiong, Xiutian Zhao, Dawei Zhu, Wenhao Wu, Ke Wang, Cheng Li, Wei Peng, Sujian Li

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

Comments Findings of EMNLP 2024

2410.07638 2024-10-11 cs.LG cs.AI cs.IT math.IT stat.ML 62%

Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits

Yunlong Hou, Vincent Y. F. Tan, Zixin Zhong

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

Comments 69 pages. Accepted to NeurIPS 2024

2410.03721 2024-10-08 cs.CL cs.AI cs.HC 62%

Thematic Analysis with Open-Source Generative AI and Machine Learning: A New Method for Inductive Qualitative Codebook Development

Andrew Katz, Gabriella Coloyan Fleming, Joyce Main

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

2410.02829 2024-10-07 cs.AI cs.HC cs.LG 62%

LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents

Chang Xiao, Brenda Z. Yang

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

2410.02717 2024-10-04 cond-mat.mtrl-sci cs.AI cs.LG 62%

Measurements with Noise: Bayesian Optimization for Co-optimizing Noise and Property Discovery in Automated Experiments

Boris N. Slautin, Yu Liu, Jan Dec, Vladimir V. Shvartsman, Doru C. Lupascu, Maxim Ziatdinov, Sergei V. Kalinin

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

Comments 22 pages, 9 figures

2409.18454 2024-09-30 cs.CL cs.AI 62%

Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications

Aditi Godbole, Jabin Geevarghese George, Smita Shandilya

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

2409.17650 2024-09-27 cs.AI cs.CL 62%

Digital Twin Ecosystem for Oncology Clinical Operations

Himanshu Pandey, Akhil Amod, Shivang, Kshitij Jaggi, Ruchi Garg, Abheet Jain, Vinayak Tantia

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

Comments Pre Print

2409.16997 2024-09-27 cs.LG cs.AI 62%

INT-FlashAttention: Enabling Flash Attention for INT8 Quantization

Shimao Chen, Zirui Liu, Zhiying Wu, Ce Zheng, Peizhuang Cong, Zihan Jiang, Yuhan Wu, Lei Su, Tong Yang

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

2211.05207 2024-09-26 cs.CV cs.AI cs.LG 62%

Improving Clinician Performance in Classification of EEG Patterns on the Ictal-Interictal-Injury Continuum using Interpretable Machine Learning

Alina Jade Barnett, Zhicheng Guo, Jin Jing, Wendong Ge, Peter W. Kaplan, Wan Yee Kong, Ioannis Karakis, Aline Herlopian, Lakshman Arcot Jayagopal, Olga Taraschenko, Olga Selioutski, Gamaleldin Osman, Daniel Goldenholz, Cynthia Rudin, M. Brandon Westover

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

Comments 24 pages including appendices, 9 figures, published at NEJM AI

Journal ref NEJM AI. 2024 Jun; 1(6): 10.1056/aioa2300331

2409.16220 2024-09-25 cs.IR cs.AI cs.CL 62%

Towards Enhancing Linked Data Retrieval in Conversational UIs using Large Language Models

Omar Mussa, Omer Rana, Benoît Goossens, Pablo Orozco-Terwengel, Charith Perera

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

Comments This paper has been accepted at the 25th International Web Information Systems Engineering Conference (WISE 2024)

2409.09191 2024-09-20 cs.LG cs.AI cs.ET 62%

ProcessTBench: An LLM Plan Generation Dataset for Process Mining

Andrei Cosmin Redis, Mohammadreza Fani Sani, Bahram Zarrin, Andrea Burattin

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

Comments 6 pages, 4 figures, dataset available at https://github.com/microsoft/ProcessTBench

2409.10964 2024-09-19 q-bio.BM cs.AI cs.LG q-bio.QM 62%

Active learning for energy-based antibody optimization and enhanced screening

Kairi Furui, Masahito Ohue

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

Comments 8 pages

2406.15540 2024-09-19 cs.SE cs.FL cs.LG 62%

Specify What? Enhancing Neural Specification Synthesis by Symbolic Methods

George Granberry, Wolfgang Ahrendt, Moa Johansson

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

2409.11350 2024-09-18 q-bio.TO cs.AI cs.LG 62%

Clinical Validation of a Real-Time Machine Learning-based System for the Detection of Acute Myeloid Leukemia by Flow Cytometry

Lauren M. Zuromski, Jacob Durtschi, Aimal Aziz, Jeffrey Chumley, Mark Dewey, Paul English, Muir Morrison, Keith Simmon, Blaine Whipple, Brendan O'Fallon, David P. Ng

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

2409.10580 2024-09-18 cs.LG cs.AI stat.ML 62%

Veridical Data Science for Medical Foundation Models

Ahmed Alaa, Bin Yu

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

2409.09044 2024-09-17 cs.AR cs.AI cs.LG 62%

ElasticAI: Creating and Deploying Energy-Efficient Deep Learning Accelerator for Pervasive Computing

Chao Qian, Tianheng Ling, Gregor Schiele

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

Comments The paper is accepted by 2023 IEEE International Conference on Pervasive Computing and Communications (Best Demo Award)

2312.08384 2024-09-17 cs.CV cs.AI cs.LG 62%

Taking it further: leveraging pseudo labels for field delineation across label-scarce smallholder regions

Philippe Rufin, Sherrie Wang, Sá Nogueira Lisboa, Jan Hemmerling, Mirela G. Tulbure, Patrick Meyfroidt

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

2404.04839 2024-09-16 cs.SE cs.AI 62%

AI for DevSecOps: A Landscape and Future Opportunities

Michael Fu, Jirat Pasuksmit, Chakkrit Tantithamthavorn

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

2401.00544 2024-09-12 cs.AI cs.LG 62%

A Reliable Knowledge Processing Framework for Combustion Science using Foundation Models

Vansh Sharma, Venkat Raman

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

Comments 38 pages and 10 figures; Fixed figure resolution

2409.00286 2024-09-09 cs.CL cs.AI 62%

OnlySportsLM: Optimizing Sports-Domain Language Models with SOTA Performance under Billion Parameters

Zexin Chen, Chengxi Li, Xiangyu Xie, Parijat Dube

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

Comments 13 pages, 4 figures, 4 tables

1. 工作流自动化 10492 篇

Rethinking Scale: The Efficacy of Fine-Tuned Open-Source LLMs in Large-Scale Reproducible Social Science Research

TaskBench: Benchmarking Large Language Models for Task Automation

Keep on Swimming: Real Attackers Only Need Partial Knowledge of a Multi-Model System

Universality of the $π^2/6$ Pathway in Avoiding Model Collapse

MatExpert: Decomposing Materials Discovery by Mimicking Human Experts

Towards Human-Centered Construction Robotics: A Reinforcement Learning-Driven Companion Robot for Contextually Assisting Carpentry Workers

Audio-to-Score Conversion Model Based on Whisper methodology

SafeLLM: Domain-Specific Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance

EasyRAG: Efficient Retrieval-Augmented Generation Framework for Automated Network Operations

Long Context Compression with Activation Beacon

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories

Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits

Thematic Analysis with Open-Source Generative AI and Machine Learning: A New Method for Inductive Qualitative Codebook Development

LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents

Measurements with Noise: Bayesian Optimization for Co-optimizing Noise and Property Discovery in Automated Experiments

Leveraging Long-Context Large Language Models for Multi-Document Understanding and Summarization in Enterprise Applications

Digital Twin Ecosystem for Oncology Clinical Operations

INT-FlashAttention: Enabling Flash Attention for INT8 Quantization

Improving Clinician Performance in Classification of EEG Patterns on the Ictal-Interictal-Injury Continuum using Interpretable Machine Learning

Towards Enhancing Linked Data Retrieval in Conversational UIs using Large Language Models

ProcessTBench: An LLM Plan Generation Dataset for Process Mining

Active learning for energy-based antibody optimization and enhanced screening

Specify What? Enhancing Neural Specification Synthesis by Symbolic Methods

Clinical Validation of a Real-Time Machine Learning-based System for the Detection of Acute Myeloid Leukemia by Flow Cytometry

Veridical Data Science for Medical Foundation Models

ElasticAI: Creating and Deploying Energy-Efficient Deep Learning Accelerator for Pervasive Computing

Taking it further: leveraging pseudo labels for field delineation across label-scarce smallholder regions

AI for DevSecOps: A Landscape and Future Opportunities

A Reliable Knowledge Processing Framework for Combustion Science using Foundation Models

OnlySportsLM: Optimizing Sports-Domain Language Models with SOTA Performance under Billion Parameters