AI Agent - arXivDaily 专题

2405.19414 2024-05-31 cs.LG 57%

Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning

Alexander Politowicz, Sahisnu Mazumder, Bing Liu

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 9 pages, 3 figures

2405.19269 2024-05-30 cs.LG 57%

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

Yuda Song, Lili Wu, Dylan J. Foster, Akshay Krishnamurthy

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 63 pages, 4 figures, published at ICML 2024

2310.12945 2024-05-30 cs.CV cs.GR cs.LG 57%

3D-GPT: Procedural 3D Modeling with Large Language Models

Chunyi Sun, Junlin Han, Weijian Deng, Xinlong Wang, Zishan Qin, Stephen Gould

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Project page: https://chuny1.github.io/3DGPT/3dgpt.html

2405.16595 2024-05-28 cs.AI cs.GT cs.NE 57%

An Evolutionary Framework for Connect-4 as Test-Bed for Comparison of Advanced Minimax, Q-Learning and MCTS

Henry Taylor, Leonardo Stella

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 8 pages, 4 figures, 1 table

2405.15786 2024-05-28 cs.IR cs.AI 57%

Enhancement of Subjective Content Descriptions by using Human Feedback

Magnus Bender, Tanya Braun, Ralf Möller, Marcel Gehrke

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2405.15561 2024-05-27 cs.HC cs.AI 57%

When Generative AI Meets Workplace Learning: Creating A Realistic & Motivating Learning Experience With A Generative PCA

Andreas Bucher, Birgit Schenk, Mateusz Dolata, Gerhard Schwabe

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Journal ref ECIS 2024

2405.15430 2024-05-27 cs.LG cs.LO 57%

Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics

David Boetius, Stefan Leue

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 7 pages + references

2405.15414 2024-05-27 cs.AI 57%

Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification

Yuxuan Guo, Shaohui Peng, Jiaming Guo, Di Huang, Xishan Zhang, Rui Zhang, Yifan Hao, Ling Li, Zikang Tian, Mingju Gao, Yutai Li, Yiming Gan, Shuai Liang, Zihao Zhang, Zidong Du, Qi Guo, Xing Hu, Yunji Chen

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2405.15083 2024-05-27 cs.AI cs.CV 57%

MuDreamer: Learning Predictive World Models without Reconstruction

Maxime Burchi, Radu Timofte

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2405.12946 2024-05-22 cs.HC cs.LG 57%

Tutorly: Turning Programming Videos Into Apprenticeship Learning Environments with LLMs

Wengxi Li, Roy Pea, Nick Haber, Hari Subramonyam

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2405.12461 2024-05-22 cs.CV cs.AI 57%

WorldAfford: Affordance Grounding based on Natural Language Instructions

Changmao Chen, Yuren Cong, Zhen Kan

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2405.12355 2024-05-22 cs.LG cs.SY eess.SY 57%

Investigating the Impact of Choice on Deep Reinforcement Learning for Space Controls

Nathaniel Hamilton, Kyle Dunlap, Kerianne L. Hobbs

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2207.04117 2024-05-22 cs.LG cs.SY eess.SY 57%

Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents

Nathaniel Hamilton, Kyle Dunlap, Taylor T Johnson, Kerianne L Hobbs

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Journal ref 2023 IEEE 9th International Conference on Space Mission Challenges for Information Technology (SMC-IT), 2023, pp. 45-55

2405.11629 2024-05-21 cs.CV cs.AI 57%

Searching Realistic-Looking Adversarial Objects For Autonomous Driving Systems

Shengxiang Sun, Shenzhe Zhu

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2106.01750 2024-05-21 cs.AI cs.SI 57%

Modeling Influencer Marketing Campaigns in Social Networks

Ronak Doshi, Ajay Ramesh Ranganathan, Shrisha Rao

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 14 pages, in IEEE Transactions on Computational Social Systems

Journal ref IEEE Transactions on Computational Social Systems, vol. 10 (1), February 2023, pp. 322--334

2402.08502 2024-05-20 cs.LG cs.SY eess.SY 57%

Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea

Hanna Krasowski, Matthias Althoff

专题命中 Agent评测：agent(abstract)；分类 cs.LG

2405.09255 2024-05-16 cs.HC cs.SE 57%

Reinforcement Learning-Based Framework for the Intelligent Adaptation of User Interfaces

Daniel Gaspar-Figueiredo, Marta Fernández-Diego, Ruben Nuredini, Silvia Abrahão, Emilio Insfrán

专题命中 Agent评测：agent(abstract)；分类 cs.SE

Comments To be published in Companion of the16th ACM SIGCHI Symposium on Engineering Interactive Computing Systems (EICS Companion '24). 9 pages, 2 figures, 28 references

2202.04294 2024-05-16 cs.LG cs.IT math.IT stat.ML 57%

Optimal Clustering with Bandit Feedback

Junwen Yang, Zixin Zhong, Vincent Y. F. Tan

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 54 pages, 4 figures

2308.10413 2024-05-16 cs.GT cs.AI 57%

Mechanisms that play a game, not toss a coin

Toby Walsh

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments To appear in Proceedings of IJCAI 2024

2404.12064 2024-05-15 cs.CV cs.LG 57%

PureForest: A Large-Scale Aerial Lidar and Aerial Imagery Dataset for Tree Species Classification in Monospecific Forests

Charles Gaydon, Floryne Roche

专题命中 Agent评测：workflow(abstract)；分类 cs.LG

Comments 14 pages | 5 figures | Dataset is available at http://huggingface.co/datasets/IGNF/PureForest | Deep learning code repository is on Gihtub at https://github.com/IGNF/myria3d | Data engineering code repository is on Github at https://github.com/IGNF/pacasam

2311.03783 2024-05-14 cs.AI cs.RO cs.SC 57%

Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI

Song Yaoxian, Sun Penglei, Liu Haoyu, Li Zhixu, Song Wei, Xiao Yanghua, Zhou Xiaofang

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 14 pages, 6 figures

2312.15965 2024-05-13 cs.LG 57%

Efficient Reinforcement Learning via Decoupling Exploration and Utilization

Jingpu Yang, Helin Wang, Qirui Zhao, Zhecheng Shi, Zirui Song, Miao Fang

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Accepted by ICIC 2024 (Oral)

Journal ref 2024 International Conference on Intelligent Computing

2405.05673 2024-05-10 cs.LG stat.ML 57%

Imprecise Multi-Armed Bandits

Vanessa Kosoy

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments MSc thesis, 174 pages

2405.04909 2024-05-09 cs.CV cs.AI 57%

Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models

Zhengxing Lan, Hongbo Li, Lingshan Liu, Bo Fan, Yisheng Lv, Yilong Ren, Zhiyong Cui

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2301.11774 2024-05-09 cs.LG 57%

Reinforcement Learning from Diverse Human Preferences

Wanqi Xue, Bo An, Shuicheng Yan, Zhongwen Xu

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments Published as a conference paper in IJCAI 2024

2405.04180 2024-05-08 cs.LG cs.CV 57%

Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models

Zhixuan Chu, Lei Zhang, Yichen Sun, Siqiao Xue, Zhibo Wang, Zhan Qin, Kui Ren

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments arXiv admin note: text overlap with arXiv:2306.08302, arXiv:2403.05131 by other authors

2405.03809 2024-05-08 cs.AI 57%

SocialFormer: Social Interaction Modeling with Edge-enhanced Heterogeneous Graph Transformers for Trajectory Prediction

Zixu Wang, Zhigang Sun, Juergen Luettin, Lavdim Halilaj

专题命中 Agent评测：agent(abstract)；分类 cs.AI

2405.03256 2024-05-07 cs.SE 57%

MARE: Multi-Agents Collaboration Framework for Requirements Engineering

Dongming Jin, Zhi Jin, Xiaohong Chen, Chunhui Wang

专题命中 Agent评测：agent(abstract)；分类 cs.SE

2405.02480 2024-05-07 econ.EM cs.AI cs.MA 57%

A Network Simulation of OTC Markets with Multiple Agents

James T. Wilkinson, Jacob Kelter, John Chen, Uri Wilensky

专题命中 Agent评测：agent(abstract)；分类 cs.AI

Comments 20 pages, 17 figures

2404.17673 2024-04-30 cs.LG cs.RO 57%

Learning Manipulation Tasks in Dynamic and Shared 3D Spaces

Hariharan Arunachalam, Marc Hanheide, Sariah Mghames

专题命中 Agent评测：agent(abstract)；分类 cs.LG

Comments 5 pages

1. Agent评测 15866 篇

Safety through Permissibility: Shield Construction for Fast and Safe Reinforcement Learning

Rich-Observation Reinforcement Learning with Continuous Latent Dynamics

3D-GPT: Procedural 3D Modeling with Large Language Models

An Evolutionary Framework for Connect-4 as Test-Bed for Comparison of Advanced Minimax, Q-Learning and MCTS

Enhancement of Subjective Content Descriptions by using Human Feedback

When Generative AI Meets Workplace Learning: Creating A Realistic & Motivating Learning Experience With A Generative PCA

Counterexample-Guided Repair of Reinforcement Learning Systems Using Safety Critics

Luban: Building Open-Ended Creative Agents via Autonomous Embodied Verification

MuDreamer: Learning Predictive World Models without Reconstruction

Tutorly: Turning Programming Videos Into Apprenticeship Learning Environments with LLMs

WorldAfford: Affordance Grounding based on Natural Language Instructions

Investigating the Impact of Choice on Deep Reinforcement Learning for Space Controls

Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents

Searching Realistic-Looking Adversarial Objects For Autonomous Driving Systems

Modeling Influencer Marketing Campaigns in Social Networks

Provable Traffic Rule Compliance in Safe Reinforcement Learning on the Open Sea

Reinforcement Learning-Based Framework for the Intelligent Adaptation of User Interfaces

Optimal Clustering with Bandit Feedback

Mechanisms that play a game, not toss a coin

PureForest: A Large-Scale Aerial Lidar and Aerial Imagery Dataset for Tree Species Classification in Monospecific Forests

Scene-Driven Multimodal Knowledge Graph Construction for Embodied AI

Efficient Reinforcement Learning via Decoupling Exploration and Utilization

Imprecise Multi-Armed Bandits

Traj-LLM: A New Exploration for Empowering Trajectory Prediction with Pre-trained Large Language Models

Reinforcement Learning from Diverse Human Preferences

Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models

SocialFormer: Social Interaction Modeling with Edge-enhanced Heterogeneous Graph Transformers for Trajectory Prediction

MARE: Multi-Agents Collaboration Framework for Requirements Engineering

A Network Simulation of OTC Markets with Multiple Agents

Learning Manipulation Tasks in Dynamic and Shared 3D Spaces