AI Agent - arXivDaily 专题

2310.07745 2024-09-30 cs.LG 57%

Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey

Gregory Palmer, Chris Parry, Daniel J. B. Harrold, Chris Willis

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 89 pages, 14 figures, 4 tables

2409.17189 2024-09-27 math.OC cs.LG 57%

Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks

Duong Thuy Anh Nguyen, Su Wang, Duong Tung Nguyen, Angelia Nedich, H. Vincent Poor

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2409.16391 2024-09-26 cs.LG cs.CV 57%

Patch-Based Contrastive Learning and Memory Consolidation for Online Unsupervised Continual Learning

Cameron Taylor, Vassilis Vassiliades, Constantine Dovrolis

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments Published in Conference on Lifelong Learning Agents (COLLAS) 2024

2212.00796 2024-09-24 eess.IV cs.LG 57%

Convolutional Long Short-Term Memory (convLSTM) for Spatio-Temporal Forecastings of Saturations and Pressure in the SACROC Field

Palash Panja, Wei Jia, Alec Nelson, Brian McPherson

专题命中记忆与上下文管理：workflow(abstract)；分类 cs.LG

Comments Petroleum Science and Technology (2024)

2409.13449 2024-09-23 cs.CL 57%

Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts

Ming Wang, Yuanzhong Liu, Xiaoyu Liang, Yijie Huang, Daling Wang, Xiaocui Yang, Sijia Shen, Shi Feng, Xiaoming Zhang, Chaofeng Guan, Yifei Zhang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.CL

Comments arXiv admin note: text overlap with arXiv:2402.16929

1906.03040 2024-09-23 cs.CY cs.LG cs.SY eess.SP eess.SY stat.ML 57%

FASTER: Fusion AnalyticS for public Transport Event Response

Sebastien Blandin, Laura Wynter, Hasan Poonawala, Sean Laguna, Basile Dura

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2409.12968 2024-09-23 cs.HC cs.AI 57%

MITHOS: Interactive Mixed Reality Training to Support Professional Socio-Emotional Interactions at Schools

Lara Chehayeb, Chirag Bhuvaneshwara, Manuel Anglet, Bernhard Hilpert, Ann-Kristin Meyer, Dimitra Tsovaltzi, Patrick Gebhard, Antje Biermann, Sinah Auchtor, Nils Lauinger, Julia Knopf, Andreas Kaiser, Fabian Kersting, Gregor Mehlmann, Florian Lingenfelser, Elisabeth André

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2401.06256 2024-09-10 cs.AI 57%

A Universal Knowledge Model and Cognitive Architecture for Prototyping AGI

Artem Sukhobokov, Evgeny Belousov, Danila Gromozdov, Anna Zenger, Ilya Popov

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2409.04467 2024-09-10 eess.SY cs.LG cs.SY 57%

State and Action Factorization in Power Grids

Gianvito Losapio, Davide Beretta, Marco Mussi, Alberto Maria Metelli, Marcello Restelli

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2307.02031 2024-09-06 cs.LG cs.DB cs.DC 57%

Improving Automatic Parallel Training via Balanced Memory Workload Optimization

Yujie Wang, Youhe Jiang, Xupeng Miao, Fangcheng Fu, Shenhan Zhu, Xiaonan Nie, Yaofeng Tu, Bin Cui

专题命中记忆与上下文管理：workflow(abstract)；分类 cs.LG

Comments arXiv admin note: substantial text overlap with arXiv:2211.13878

2406.09835 2024-09-02 cs.LG 57%

I Know How: Combining Prior Policies to Solve New Tasks

Malio Li, Elia Piccoli, Vincenzo Lomonaco, Davide Bacciu

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments 7 pages, Conference on Games (CoG) 2024

2408.16632 2024-08-30 cs.NE cs.AI 57%

Maelstrom Networks

Matthew Evanusa, Cornelia Fermüller, Yiannis Aloimonos

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2304.14326 2024-08-30 cs.LG 57%

A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints

Jacopo Germano, Francesco Emanuele Stradi, Gianmarco Genalti, Matteo Castiglioni, Alberto Marchesi, Nicola Gatti

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2408.14224 2024-08-27 cs.AI 57%

Fact Probability Vector Based Goal Recognition

Nils Wilken, Lea Cohausz, Christian Bartelt, Heiner Stuckenschmidt

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Will be presented at ECAI 2024

2408.12866 2024-08-26 cs.CR cs.AI 57%

Obfuscated Memory Malware Detection

Sharmila S P, Aruna Tiwari, Narendra S Chaudhari

专题命中记忆与上下文管理：tool use(abstract)；分类 cs.AI

Comments 8 pages 9 figures presented in IEEE CCEM Conference paper

2309.11984 2024-08-09 cs.RO cs.AI 57%

State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping

Panagiotis Petropoulakis, Ludwig Gräf, Mohammadhossein Malmir, Josip Josifovski, Alois Knoll

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments Accepted to IEEE International Conference on Systems, Man, and Cybernetics (SMC) 2024

2309.11651 2024-08-09 eess.SY cs.LG cs.SY math.AP math.OC 57%

Drift Control of High-Dimensional RBM: A Computational Method Based on Neural Networks

Baris Ata, J. Michael Harrison, Nian Si

专题命中记忆与上下文管理：planning(abstract)；分类 cs.LG

2403.07632 2024-08-08 cs.LG q-bio.BM 57%

CardioGenAI: A Machine Learning-Based Framework for Re-Engineering Drugs for Reduced hERG Liability

Gregory W. Kyro, Matthew T. Martin, Eric D. Watt, Victor S. Batista

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2408.00818 2024-08-05 cs.AI cs.SI 57%

Y Social: an LLM-powered Social Media Digital Twin

Giulio Rossetti, Massimo Stella, Rémy Cazabet, Katherine Abramski, Erica Cau, Salvatore Citraro, Andrea Failla, Riccardo Improta, Virginia Morini, Valentina Pansanella

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 29 pages, 5 figures

2407.19371 2024-07-30 cs.LG 57%

Deep State-Space Generative Model For Correlated Time-to-Event Predictions

Yuan Xue, Denny Zhou, Nan Du, Andrew M. Dai, Zhen Xu, Kun Zhang, Claire Cui

专题命中记忆与上下文管理：planning(abstract)；分类 cs.LG

Comments Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

2407.05781 2024-07-30 cs.LG cs.SY eess.SY 57%

Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control

Bruce D. Lee, Leonardo F. Toso, Thomas T. Zhang, James Anderson, Nikolai Matni

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2308.16891 2024-07-30 cs.RO cs.CV cs.LG 57%

GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields

Yanjie Ze, Ge Yan, Yueh-Hua Wu, Annabella Macaluso, Yuying Ge, Jianglong Ye, Nicklas Hansen, Li Erran Li, Xiaolong Wang

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments CoRL 2023 Oral. Website: https://yanjieze.com/GNFactor/

2407.13364 2024-07-19 cs.LG 57%

Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction

Riccardo De Santi, Federico Arangath Joseph, Noah Liniger, Mirco Mutti, Andreas Krause

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments ICML 2024

2407.13091 2024-07-19 cs.AI cs.IR 57%

On Causally Disentangled State Representation Learning for Reinforcement Learning based Recommender Systems

Siyu Wang, Xiaocong Chen, Lina Yao

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

2404.05449 2024-07-19 cs.CL 57%

RoT: Enhancing Large Language Models with Reflection on Search Trees

Wenyang Hui, Kewei Tu

专题命中记忆与上下文管理：planning(abstract)；分类 cs.CL

Comments 9 pages main

2407.10512 2024-07-16 q-bio.NC cs.LG eess.IV 57%

MARVEL: MR Fingerprinting with Additional micRoVascular Estimates using bidirectional LSTMs

Antoine Barrier, Thomas Coudert, Aurélien Delphin, Benjamin Lemasson, Thomas Christen

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2407.06088 2024-07-09 cs.AI 57%

Qualitative Event Perception: Leveraging Spatiotemporal Episodic Memory for Learning Combat in a Strategy Game

Will Hancock, Kenneth D. Forbus

专题命中记忆与上下文管理：agent(abstract)；分类 cs.AI

Comments 16 pages, 10 figures

2406.19768 2024-07-02 cs.LG 57%

Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors

Emma Cramer, Bernd Frauenknecht, Ramil Sabirov, Sebastian Trimpe

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

2406.18805 2024-06-28 cs.LG cs.GT 57%

Online Stackelberg Optimization via Nonlinear Control

William Brown, Christos Papadimitriou, Tim Roughgarden

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments COLT 2024

2312.02739 2024-06-28 cs.LG 57%

LExCI: A Framework for Reinforcement Learning with Embedded Systems

Kevin Badalian, Lucas Koch, Tobias Brinkmann, Mario Picerno, Marius Wegener, Sung-Yong Lee, Jakob Andert

专题命中记忆与上下文管理：agent(abstract)；分类 cs.LG

Comments The code, models, and data used for this work are available in a separate branch of LExCI's GitHub repository (https://github.com/mechatronics-RWTH/lexci-2/tree/lexci_paper). This paper has been submitted to Applied Intelligence (https://link.springer.com/journal/10489). 2024-06-27: Updated the footnote on the title page so that it provides information about the paper's Version of Record

Journal ref Applied Intelligence (2024)

1. 记忆与上下文管理 4758 篇

Deep Reinforcement Learning for Autonomous Cyber Defence: A Survey

Decentralized Federated Learning with Gradient Tracking over Time-Varying Directed Networks

Patch-Based Contrastive Learning and Memory Consolidation for Online Unsupervised Continual Learning

Convolutional Long Short-Term Memory (convLSTM) for Spatio-Temporal Forecastings of Saturations and Pressure in the SACROC Field

Minstrel: Structural Prompt Generation with Multi-Agents Coordination for Non-AI Experts

FASTER: Fusion AnalyticS for public Transport Event Response

MITHOS: Interactive Mixed Reality Training to Support Professional Socio-Emotional Interactions at Schools

A Universal Knowledge Model and Cognitive Architecture for Prototyping AGI

State and Action Factorization in Power Grids

Improving Automatic Parallel Training via Balanced Memory Workload Optimization

I Know How: Combining Prior Policies to Solve New Tasks

Maelstrom Networks

A Best-of-Both-Worlds Algorithm for Constrained MDPs with Long-Term Constraints

Fact Probability Vector Based Goal Recognition

Obfuscated Memory Malware Detection

State Representations as Incentives for Reinforcement Learning Agents: A Sim2Real Analysis on Robotic Grasping

Drift Control of High-Dimensional RBM: A Computational Method Based on Neural Networks

CardioGenAI: A Machine Learning-Based Framework for Re-Engineering Drugs for Reduced hERG Liability

Y Social: an LLM-powered Social Media Digital Twin

Deep State-Space Generative Model For Correlated Time-to-Event Predictions

Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control

GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fields

Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction

On Causally Disentangled State Representation Learning for Reinforcement Learning based Recommender Systems

RoT: Enhancing Large Language Models with Reflection on Search Trees

MARVEL: MR Fingerprinting with Additional micRoVascular Estimates using bidirectional LSTMs

Qualitative Event Perception: Leveraging Spatiotemporal Episodic Memory for Learning Combat in a Strategy Game

Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors

Online Stackelberg Optimization via Nonlinear Control

LExCI: A Framework for Reinforcement Learning with Embedded Systems