AI Agent - arXivDaily 专题

2412.07981 2025-10-20 cs.AI 92%

Where Common Knowledge Cannot Be Formed, Common Belief Can -- Planning with Multi-Agent Belief Using Group Justified Perspectives

Guang Hu, Tim Miller, Nir Lipovetzky

专题命中规划决策：agent(title,abstract)；planning(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

Comments 12 pages, including supplementary and reference

2510.04886 2025-10-20 cs.AI cs.MA 88%

Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution

Adi Banerjee, Anirudh Nair, Tarik Borogovac

机构 * Amazon Web Services（亚马逊网络服务）

专题命中规划决策：agent(title,abstract)；multi-agent(title,abstract)；分类 cs.AI

2509.02444 2025-10-20 cs.AI cs.CL cs.CV cs.HC 88%

AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent

Jingru Fan, Yufan Dang, Jingyao Wu, Huatao Li, Runde Yang, Xiyuan Yang, Yuheng Wang, Chen Qian

专题命中规划决策：agent(title,abstract)；planning(abstract)；function calling(abstract)；multi-agent(abstract)

Comments Project at https://github.com/OpenBMB/AppCopilot

2412.07941 2025-10-20 cs.AI 85%

Beyond Static Assumptions: the Predictive Justified Perspective Model for Epistemic Planning

Guang Hu, Weijia Li, Yangmengfei Xu

专题命中规划决策：planning(title,abstract)；agent(abstract)；multi-agent(abstract)；分类 cs.AI

Comments 10 pages includes appendix and reference

2510.15831 2025-10-20 cs.CV 82%

VISTA: A Test-Time Self-Improving Video Generation Agent

Do Xuan Long, Xingchen Wan, Hootan Nakhost, Chen-Yu Lee, Tomas Pfister, Sercan Ö. Arık

机构 * Google（谷歌）

专题命中规划决策：agent(title,abstract)；multi-agent(abstract)

2510.15283 2025-10-20 cs.CL cs.AI 81%

Exemplar-Guided Planing: Enhanced LLM Agent for KGQA

Jingao Xu, Shuoyoucheng Ma, Xin Song, Rong Jiang, Hongkui Tu, Bin Zhou

机构 * College of Computer Science and Technology, National University of Defense Technology, Changsha, China（计算机科学与技术学院，国防科技大学，长沙，中国）

专题命中规划决策：agent(title)；planning(abstract)；分类 cs.AI、cs.CL

2510.15047 2025-10-20 cs.LG cs.CL 81%

Internalizing World Models via Self-Play Finetuning for Agentic RL

Shiqi Chen, Tongyao Zhu, Zian Wang, Jinghan Zhang, Kangrui Wang, Siyang Gao, Teng Xiao, Yee Whye Teh, Junxian He, Manling Li

机构 * City University of Hong Kong（香港城市大学）； Northwestern University（西北大学）； The Hong Kong University of Science and Technology（香港科学与技术大学）； Oxford University（牛津大学）； Allen Institute for AI (AI2)（人工智能研究所）； University of Washington（华盛顿大学）； National University of Singapore（新加坡国立大学）； The Hong Kong Polytechnic University（香港理工大学）

专题命中规划决策：agentic(title)；agent(abstract)；分类 cs.CL、cs.LG

2510.15505 2025-10-20 cs.RO 78%

Perfect Prediction or Plenty of Proposals? What Matters Most in Planning for Autonomous Driving

Aron Distelzweig, Faris Janjoš, Oliver Scheel, Sirish Reddy Varra, Raghu Rajan, Joschka Boedecker

机构 * Department of Computer Science, University of Freiburg（弗赖堡大学计算机科学系）； Bosch Center for Artificial Intelligence（博世人工智能中心）； RWTH Aachen University（亚琛工业大学）

专题命中规划决策：planning(title,abstract)

Comments 8 pages, 5 figures

2409.18641 2025-10-20 cs.RO cs.SY eess.SY 78%

Pseudo-Kinematic Trajectory Control and Planning of Tracked Vehicles

Michele Focchi, Daniele Fontanelli, Davide Stocco, Riccardo Bussola, Luigi Palopoli

机构 * Dipartimento di Ingegneria and Scienza dell'Informazione (DISI), University of Trento（信息工程系（DISI），特伦托大学）； Dipartimento di Ingegneria Industriale (DII), University of Trento（工业工程系（DII），特伦托大学）

专题命中规划决策：planning(title,abstract)

1905.00495 2025-10-20 cs.RO cs.SY eess.SY 78%

A Modular Framework for Motion Planning using Safe-by-Design Motion Primitives

Marijan Vukosavljev, Zachary Kroeze, Angela P. Schoellig, Mireille E. Broucke

专题命中规划决策：planning(title,abstract)

Comments 20 pages, 13 figures, video: http://tiny.cc/modular-3alg; accepted to Transactions on Robotics

2506.17462 2025-10-20 cs.RO cs.AI cs.CV 77%

General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting

Bernard Lange, Anil Yildiz, Mansur Arief, Shehryar Khattak, Mykel Kochenderfer, Georgios Georgakis

机构 * Stanford University（斯坦福大学）； Jet Propulsion Laboratory（喷气推进实验室）； California Institute of Technology（加州理工学院）

专题命中规划决策：agent(abstract)；planning(abstract)；agentic(abstract)；分类 cs.AI

2504.00010 2025-10-20 cs.LG cs.GR cs.MA 77%

LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration

Yuyao Zhang, Jinghao Li, Yu-Wing Tai

机构 * Dartmouth College（达特茅斯学院）； CUHK（香港大学）

专题命中规划决策：agent(abstract)；autonomous agent(abstract)；planning(abstract)；分类 cs.LG

Comments 26 pages

2501.06262 2025-10-20 cs.RO cs.AI eess.IV 77%

Towards smart and adaptive agents for active sensing on edge devices

Devendra Vyas, Nikola Pižurica, Nikola Milović, Igor Jovančević, Miguel de Prado, Tim Verbelen

机构 * Computer Science Center, U. of Montenegro（蒙特内格罗大学计算机科学中心）

专题命中规划决策：agent(abstract)；planning(abstract)；agentic(abstract)；分类 cs.AI

2506.09080 2025-10-20 cs.LG cs.AI q-fin.CP 73%

FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making

Jiaxiang Chen, Mingxi Zou, Zhuo Wang, Qifan Wang, Dongning Sun, Chi Zhang, Zenglin Xu

机构 * Fudan University（复旦大学）； Tensorpacific ； Peng Cheng Laboratory（鹏城实验室）； Meta AI ； Shanghai Academy of AI for Science (SAIS)（上海人工智能科学研究院）

专题命中规划决策：agent(abstract)；multi-agent(abstract)；分类 cs.AI、cs.LG

2505.07176 2025-10-20 cs.MA cs.AI 70%

Internet of Agents: Fundamentals, Applications, and Challenges

Yuntao Wang, Shaolong Guo, Yanghe Pan, Zhou Su, Fahao Chen, Tom H. Luan, Peng Li, Jiawen Kang, Dusit Niyato

机构 * School of Cyber Science and Engineering, Xi'an Jiaotong University（网络安全科学与工程学院，西安交通大学）； School of Artificial Intelligence, Shandong University（人工智能学院，山东大学）； School of Automation, Guangdong University of Technology（自动化学院，广东技术大学）； College of Computing and Data Science, Nanyang Technological University（计算与数据科学学院，南洋理工大学）

专题命中规划决策：agent(abstract)；AI agent(abstract)；分类 cs.AI

Comments 25 pages,10 figures, 10 tables. Accepted by IEEE TCCN in Oct. 2025

2504.02679 2025-10-20 eess.SY cs.SY 67%

A Set-Theoretic Robust Control Approach for Linear Quadratic Games with Unknown Counterparts

Francesco Bianchin, Robert Lefringhausen, Elisa Gaetan, Samuel Tesfazgi, Sandra Hirche

专题命中规划决策：agent(abstract)；multi-agent(abstract)

Comments Accepted for publication in the Proceedings of the 64th IEEE Conference on Decision and Control

2510.15728 2025-10-20 cs.LG cs.AI 62%

RLAF: Reinforcement Learning from Automaton Feedback

Mahyar Alinejad, Alvaro Velasquez, Yue Wang, George Atia

机构 * University of Central Florida（中央佛罗里达大学）； University of Colorado Boulder（科罗拉多大学博尔德分校）

专题命中规划决策：agent(abstract)；分类 cs.AI、cs.LG

2510.15502 2025-10-20 cs.LG cs.AI 62%

The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling

Shijia Kang, Muhan Zhang

机构 * Institute for Artificial Intelligence（人工智能研究院）

专题命中规划决策：agent(abstract)；分类 cs.AI、cs.LG

2510.14837 2025-10-20 cs.LG cs.AI 62%

Reinforcement Learning with Stochastic Reward Machines

Jan Corazza, Ivan Gavran, Daniel Neider

机构 * University of Zagreb（Zagreb大学）； Max Planck Institute for Software Systems（软件系统马克斯·普朗克研究所）

专题命中规划决策：agent(abstract)；分类 cs.AI、cs.LG

Comments A shorter version of this paper appeared in the Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI-22). Source code available at https://github.com/corazza/srm

Journal ref Corazza, J., Gavran, I., & Neider, D. (2022). Reinforcement Learning with Stochastic Reward Machines. Proceedings of the AAAI Conference on Artificial Intelligence, 36(6), 6429-6436

2510.15120 2025-10-20 cs.AI 57%

Procedural Game Level Design with Deep Reinforcement Learning

Miraç Buğra Özkan

机构 * Istanbul Technical University Artificial Intelligence（伊斯坦布尔技术大学人工智能）

专题命中规划决策：agent(abstract)；分类 cs.AI

Comments 11 pages, 10 figures, IEEE conference format

2510.15056 2025-10-20 cs.LG 57%

Learn to Change the World: Multi-level Reinforcement Learning with Model-Changing Actions

Ziqing Lu, Babak Hassibi, Lifeng Lai, Weiyu Xu

机构 * University of Iowa（爱荷华大学）； University of California, Davis（加州大学戴维斯分校）

专题命中规划决策：agent(abstract)；分类 cs.LG

2510.13023 2025-10-20 cs.LG physics.comp-ph 57%

Machine Learning-Based Ultrasonic Weld Characterization Using Hierarchical Wave Modeling and Diffusion-Driven Distribution Alignment

Joshua R. Tempelman, Adam J. Wachtor, Eric B. Flynn

机构 * Data Science Group, Los Alamos National Laboratory, Los Alamos NM, USA（数据科学组，洛斯阿拉莫斯国家实验室）； Engineering Institute, Los Alamos National Laboratory, Los Alamos NM, USA（工程学院，洛斯阿拉莫斯国家实验室）

专题命中规划决策：workflow(abstract)；分类 cs.LG

Comments 26 pages, 6 page appendix

2510.11620 2025-10-20 cs.CL 57%

Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation

Siheng Xiong, Ali Payani, Faramarz Fekri

机构 * Georgia Institute of Technology（佐治亚理工学院）； Cisco Research（思科研究）

专题命中规划决策：planning(abstract)；分类 cs.CL

2510.07581 2025-10-20 cs.LG 57%

Expanding the Action Space of LLMs to Reason Beyond Language

Zhongqi Yue, Weishi Wang, Yundaichuan Zhan, Juncheng Li, Daniel Dahlmeier, Fredrik D. Johansson

机构 * Chalmers University of Technology and University of Gothenburg（查尔姆斯理工大学和哥德堡大学）； SAP（SAP公司）； Zhejiang University（浙江大学）

专题命中规划决策：planning(abstract)；分类 cs.LG

2507.19983 2025-10-20 cs.RO cs.AI 57%

CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints

Yuhong Deng, Chao Tang, Cunjun Yu, Linfeng Li, David Hsu

机构 * School of Computing, Smart System Institute, National University of Singapore, Singapore（计算学院、智能系统研究所、新加坡国立大学，新加坡）； Department of Electronic and Electrical Engineering, Southern University of Science and Technology, China（电子与电气工程系、南方科技大学，中国）

专题命中规划决策：planning(abstract)；分类 cs.AI

2506.16971 2025-10-20 eess.SY cs.AI cs.MA cs.SY 57%

Formal Control for Uncertain Systems via Contract-Based Probabilistic Surrogates (Extended Version)

Oliver Schön, Sofie Haesaert, Sadegh Soudjani

机构 * Newcastle University（新castle大学）； Eindhoven University of Technology（埃因霍温理工大学）； Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）

专题命中规划决策：agent(abstract)；分类 cs.AI

Comments 26 pages, 5 figures, extended version of paper accepted for publication at QEST 2025

2503.15407 2025-10-20 eess.SY cs.LG cs.SY 57%

Exploiting Prior Knowledge in Preferential Learning of Individualized Autonomous Vehicle Driving Styles

Lukas Theiner, Sebastian Hirt, Alexander Steinke, Rolf Findeisen

机构 * Control and Cyber-Physical Systems Laboratory, Technical University of Darmstadt（控制与物理信息系统实验室，德累斯顿技术大学）

专题命中规划决策：planning(abstract)；分类 cs.LG

Comments 6 pages, 6 figures, accepted for ECC 2025

1905.00406 2025-10-20 cs.LG cs.SY eess.SY stat.ML 57%

Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman Filter

Xi Xiong, Kaan Ozbay, Li Jin, Chen Feng

专题命中规划决策：planning(abstract)；分类 cs.LG

cs/0409056 2025-10-20 math.NA cs.CE cs.NA physics.comp-ph 50%

Using sparse matrices and splines-based interpolation in computational fluid dynamics simulations

Gianluca Argentini

专题命中规划决策：planning(abstract)

Comments Talk at SIMAI (Societa' Italiana di Matematica Applicata e Industriale) 2004 Congress, Venice, San Servolo Island, September 20-24, 2004

cs/0404047 2025-10-20 math.NA cs.DC cs.NA physics.comp-ph 50%

Using matrices in post-processing phase of CFD simulations

Gianluca Argentini

专题命中规划决策：planning(abstract)

Comments Paper based on presentation-talk at SCICOMP9, Bologna (Italy), March 23-26, 2004; workshop organized by IBM, CINECA (Italy) (dr. Sigismondo Boschi, dr. Giovanni Erbacci), NERSC-DOE (USA) (dr. David Skinner), web site: www.spscicomp.org ; main topics: Computational Fluid Dynamics

Journal ref Progress in Industrial Mathematics at ECMI 2004 - Eindhoven (Netherlands), Springer, 2005

1. 规划决策 38 篇

Where Common Knowledge Cannot Be Formed, Common Belief Can -- Planning with Multi-Agent Belief Using Group Justified Perspectives

Where Did It All Go Wrong? A Hierarchical Look into Multi-Agent Error Attribution

AppCopilot: Toward General, Accurate, Long-Horizon, and Efficient Mobile Agent

Beyond Static Assumptions: the Predictive Justified Perspective Model for Epistemic Planning

VISTA: A Test-Time Self-Improving Video Generation Agent

Exemplar-Guided Planing: Enhanced LLM Agent for KGQA

Internalizing World Models via Self-Play Finetuning for Agentic RL

Perfect Prediction or Plenty of Proposals? What Matters Most in Planning for Autonomous Driving

Pseudo-Kinematic Trajectory Control and Planning of Tracked Vehicles

A Modular Framework for Motion Planning using Safe-by-Design Motion Primitives

General-Purpose Robotic Navigation via LVLM-Orchestrated Perception, Reasoning, and Acting

LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration

Towards smart and adaptive agents for active sensing on edge devices

FinHEAR: Human Expertise and Adaptive Risk-Aware Temporal Reasoning for Financial Decision-Making

Internet of Agents: Fundamentals, Applications, and Challenges

A Set-Theoretic Robust Control Approach for Linear Quadratic Games with Unknown Counterparts

RLAF: Reinforcement Learning from Automaton Feedback

The Road Less Traveled: Enhancing Exploration in LLMs via Sequential Sampling

Reinforcement Learning with Stochastic Reward Machines

Procedural Game Level Design with Deep Reinforcement Learning

Learn to Change the World: Multi-level Reinforcement Learning with Model-Changing Actions

Machine Learning-Based Ultrasonic Weld Characterization Using Hierarchical Wave Modeling and Diffusion-Driven Distribution Alignment

Enhancing Long Chain-of-Thought Reasoning through Multi-Path Plan Aggregation

Expanding the Action Space of LLMs to Reason Beyond Language

CLASP: General-Purpose Clothes Manipulation with Semantic Keypoints

Formal Control for Uncertain Systems via Contract-Based Probabilistic Surrogates (Extended Version)

Exploiting Prior Knowledge in Preferential Learning of Individualized Autonomous Vehicle Driving Styles

Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman Filter

Using sparse matrices and splines-based interpolation in computational fluid dynamics simulations

Using matrices in post-processing phase of CFD simulations