arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

AI Agent

智能体、工具调用、规划、工作流、多智能体和自主任务执行。

共收录 4766 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 记忆与上下文管理 4766 篇

2511.20863 2025-11-27 physics.chem-ph 50%

Bridging Atomistic and Mesoscale Lithium Transport via Machine-Learned Force Fields and Markov State Models

通过机器学习力场和马尔可夫状态模型桥接原子尺度和介观尺度的锂传输

Muhammad Nawaz Qaisrani, Christoph Kirsch, Aaron Flötotto, Jonas Hänseroth, Jules Oumard, Daniel Sebastiani, Christian Dreßler

专题命中 记忆与上下文管理 :workflow(abstract)

AI总结 通过机器学习力场和马尔可夫状态模型,建立原子尺度与介观尺度锂传输的定量联系,揭示稀有扩散过程和传输路径。

Comments 36 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20606 2025-11-27 q-fin.TR cs.MA cs.SI 50%

Limit Order Book Dynamics in Matching Markets: Microstructure, Spread, and Execution Slippage

匹配市场中的限价簿动态:微观结构、买卖价差与执行滑点

Yao Wu

专题命中 记忆与上下文管理 :agent(abstract)

AI总结 本文提出了一种基于限价簿的市场微观结构模型,揭示了买卖价差和执行滑点在匹配失败中的作用机制。

Comments 33 pages, 7 figures, 5 experiments, 6 appendices. Primary category: q-fin.TR; Secondary: cs.SI. Code: https://github.com/Republic1024/Limit-Order-Matching-Microstructure

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20552 2025-11-26 eess.SY cs.SY 50%

From Features to States: Data-Driven Selection of Measured State Variables via RFE-DMDc

从特征到状态:通过RFE-DMDc进行数据驱动的测量状态变量选择

Haoyu Wang, Andrea Alfonsi, Roberto Ponciroli, Richard Vilim

专题命中 记忆与上下文管理 :workflow(abstract)

AI总结 本文提出RFE-DMDc方法,通过递归特征消除和动态模式分解,实现数据驱动的状态变量选择,提高模型预测精度和计算效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18664 2025-11-26 econ.GN q-fin.EC 50%

Clarifying Trinko as Precedent in EHR and AI Memory Duty to Deal Cases: A New Institutional Economics Approach

澄清Trinko在电子健康记录和AI记忆义务案件中的先例地位:一种新的制度经济学方法

Lawrence W. Abrams

专题命中 记忆与上下文管理 :agentic(abstract)

AI总结 本文通过制度经济学方法澄清Trinko案在电子健康记录和AI记忆义务案件中的先例地位,旨在减少引用错误并提高法律适用性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19520 2025-11-26 physics.bio-ph cs.NE q-bio.NC 50%

Modeling Bioelectric State Transitions in Glial Cells: An ASAL-Inspired Computational Approach to Glioblastoma Initiation

胶质细胞生物电状态转换建模:一种受ASAL启发的计算方法用于胶母瘤发生

Wiktoria Agata Pawlak

专题命中 记忆与上下文管理 :agent(abstract)

AI总结 本文提出了一种基于代理的计算方法,通过模拟胶质细胞生物电状态转换,揭示线粒体功能障碍和生物电信号破坏在胶母瘤发生中的作用。

Comments Thesis preprint. arXiv category: cs.NE

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19038 2025-11-25 math.OC math.AP 50%

Deterministic Mean Field Games on Networks and Related Optimal Control Problems

网络上的确定性均场博弈及相关最优控制问题

Yves Achdou, Claudio Marchi, Nicoletta Tchou

专题命中 记忆与上下文管理 :agent(abstract)

AI总结 本文研究了网络上的确定性均场博弈及相关最优控制问题,提出了一种基于拉格朗日公式的松弛均衡方法,并获得了价值函数和概率测度的弱解。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17054 2025-11-24 cs.CV 50%

RL-AD-Net: Reinforcement Learning Guided Adaptive Displacement in Latent Space for Refined Point Cloud Completion

RL-AD-Net: 基于强化学习的潜在空间自适应位移用于精细化点云补全

Bhanu Pratap Paregi, Vaibhav Kumar

机构 * GeoAI4Cities Lab, IISER Bhopal(GeoAI4Cities实验室,印度Bhopal IISER)

专题命中 记忆与上下文管理 :agent(abstract)

AI总结 RL-AD-Net通过强化学习在潜在空间中优化点云补全,提升局部几何一致性,适用于多种补全网络。

详情

展开后加载摘要…

URL PDF HTML 收藏
2309.12141 2025-11-20 physics.soc-ph cond-mat.stat-mech cs.SI nlin.AO q-bio.PE 50%

Guided rewiring of social networks reduces polarization and accelerates collective action

Jordan P. Everall, Lilli Frei, Andrew K. Ringsmuth

专题命中 记忆与上下文管理 :agent(abstract)

Comments 20 pages, 4 figures, 1 table

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12270 2025-11-18 cs.CV 50%

TM-UNet: Token-Memory Enhanced Sequential Modeling for Efficient Medical Image Segmentation

Yaxuan Jiao, Qing Xu, Yuxiang Luo, Xiangjian He, Zhen Chen, Wenting Duan

机构 * Dalian University of Technology(大连理工大学) University of Lincoln(林肯大学) University of Nottingham(诺丁汉大学) Waseda University(早稻田大学) University of Nottingham Ningbo China(宁波诺丁汉大学) Yale University(耶鲁大学)

专题命中 记忆与上下文管理 :planning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.08427 2025-11-14 cs.RO 50%

Stochastic Adaptive Estimation in Polynomial Curvature Shape State Space for Continuum Robots

Guoqing Zhang, Long Wang

机构 * Department of Mechanical Engineering, Stevens Institute of Technology(机械工程系,史蒂文斯理工学院)

专题命中 记忆与上下文管理 :planning(abstract)

Comments 20 pages. IEEE Transactions on Robotics - Accepted; this arXiv version corresponds to the final revision. Supplementary appendix provided as an ancillary PDF

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07051 2025-11-11 cs.CV cs.CR 50%

Improving Deepfake Detection with Reinforcement Learning-Based Adaptive Data Augmentation

Yuxuan Zhou, Tao Yu, Wen Huang, Yuheng Zhang, Tao Dai, Shu-Tao Xia

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02317 2025-11-11 math.OC 50%

Fiedler-Based Characterization and Identification of Leaders in Semi-Autonomous Networks

Evyatar Matmon, Daniel Zelazo

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.01389 2025-11-11 cs.MA cs.GT 50%

Optimal Strategy Revision in Population Games: A Mean Field Game Theory Perspective

Julian Barreiro-Gomez, Shinkyu Park

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.15119 2025-11-11 math.OC 50%

Mean Field LQG Social Optimization: A Reinforcement Learning Approach

Zhenhui Xu, Bing-Chang Wang, Tielong Shen

专题命中 记忆与上下文管理 :agent(abstract)

Comments 16 pages

Journal ref Automatica 172 (2025): 111924

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.05242 2025-11-10 math.OC 50%

Guaranteeing Both Consensus and Optimality in Decentralized Nonconvex Optimization with Multiple Local Updates

Jie Liu, Zuang Wang, Yongqiang Wang

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.04802 2025-11-07 cond-mat.soft physics.bio-ph physics.flu-dyn 50%

Unified description of viscous, viscoelastic, or elastic thin active films on substrates

Henning Reinken, Andreas M. Menzel

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.03305 2025-11-06 cs.IT math.IT 50%

DRL-Based Robust Multi-Timescale Anti-Jamming Approaches under State Uncertainty

Haoqin Zhao, Zan Li, Jiangbo Si, Rui Huang, Hang Hu, Tony Q. S. Quek, Naofal Al-Dhahir

专题命中 记忆与上下文管理 :agent(abstract)

Comments 13pages,12figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2410.18167 2025-11-06 quant-ph 50%

Reconstructing thermal states using dimensionally limited probes : A Model for Limited Control & Memory in Quantum Thermodynamics

Jake Xuereb, A. de Oliveira Junior, Fabien Clivaz, Pharnam Bakhshinezhad, Marcus Huber

专题命中 记忆与上下文管理 :agent(abstract)

Comments v2: 10 + 19 pages, 8 Figures, Overhauled presentation, New Example, Comments welcome!

详情

展开后加载摘要…

URL PDF HTML 收藏
1903.08255 2025-11-06 physics.soc-ph cs.CY econ.GN q-fin.EC 50%

Markov Chain Models of Refugee Migration Data

Vincent Huang, James Unwin

专题命中 记忆与上下文管理 :agent(abstract)

Comments 21 Pages, 7 Figures

Journal ref IMA Journal of Applied Mathematics, Volume 85, Issue 6, December 2020, Pages 892-912

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.02636 2025-11-05 quant-ph 50%

Adaptive Quantum Matter: Variational Organization through Ising Agents

Lakshya Nagpal, Syed. R. Hassan

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.27107 2025-11-03 cs.AR 50%

A Memory-Efficient Retrieval Architecture for RAG-Enabled Wearable Medical LLMs-Agents

Zhipeng Liao, Kunming Shao, Jiangnan Yu, Liang Zhao, Tim Kwang-Ting Cheng, Chi-Ying Tsui, Jie Yang, Mohamad Sawan

专题命中 记忆与上下文管理 :AI agent(abstract)

Comments Accepted by BioCAS2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.26033 2025-10-31 cs.GT 50%

Engineering Social Optimality via Utility Shaping in Non-Cooperative Games under Incomplete Information and Imperfect Monitoring

David Smith, Jie Dong, Yizhou Yang

专题命中 记忆与上下文管理 :agentic(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.23537 2025-10-28 math.OC 50%

Approximately optimal distributed controls for high-dimensional stochastic systems with pairwise interaction through controls

Elise Devey

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20261 2025-10-24 cs.RO cs.CV 50%

Kinaema: a recurrent sequence model for memory and pose in motion

Mert Bulent Sariyildiz, Philippe Weinzaepfel, Guillaume Bono, Gianluca Monaci, Christian Wolf

专题命中 记忆与上下文管理 :agent(abstract)

Comments 10 pages + references + checklist + appendix, 29 pages total

Journal ref Neural Information Processing Systems (NeurIPS) 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.15656 2025-10-20 nlin.AO cond-mat.stat-mech 50%

Active matter synchronization and synergetics

Frank Schweitzer, Georges Andres, Adrien Baut, Giona Casiraghi, Christoph Gote, Ramona Roller

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12749 2025-10-15 cs.CV 50%

SPORTS: Simultaneous Panoptic Odometry, Rendering, Tracking and Segmentation for Urban Scenes Understanding

Zhiliu Yang, Jinyu Dai, Jianyuan Zhang, Zhu Yang

机构 * School of Information Science and Engineering, Yunnan University(云南大学信息科学与工程学院) Yunnan University(云南大学) School of Information and Electronics, Beijing Institute of Technology(北京理工大学信息与电子学院) Yunnan Key Laboratory of Intelligent Systems and Computing(智能系统与计算重点实验室)

专题命中 记忆与上下文管理 :AI agent(abstract)

Comments Accepted by IEEE Transactions on Multimedia

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12422 2025-10-15 cs.CV 50%

VideoLucy: Deep Memory Backtracking for Long Video Understanding

Jialong Zuo, Yongtai Deng, Lingdong Kong, Jingkang Yang, Rui Jin, Yiwei Zhang, Nong Sang, Liang Pan, Ziwei Liu, Changxin Gao

机构 * National Key Laboratory of Multispectral Information Intelligent Processing Technology, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology(多谱段信息智能处理国家级重点实验室,人工智能与自动化学院,华中科技大学) NUS(国立大学新加坡) S-Lab, NTU(NTU的S实验室) Shanghai AI Lab(上海人工智能实验室)

专题命中 记忆与上下文管理 :agent(abstract)

Comments NeurIPS-2025 Accepted Paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.15595 2025-10-14 cs.RO 50%

Grasping Deformable Objects via Reinforcement Learning with Cross-Modal Attention to Visuo-Tactile Inputs

Yonghyun Lee, Sungeun Hong, Min-gu Kim, Gyeonghwan Kim, Changjoo Nam

机构 * Dept. of Electronic Engineering at Sogang University(ソガン大学电子工程系) Dept. of Immersive Media and Engineering at Sungkyunkwan University(顺天大学沉浸媒体与工程系) College of Medicine, Yonsei University(延世大学医学院)

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.03014 2025-10-14 cs.HC 50%

Survey of Large Language Models in Extended Reality: Technical Paradigms and Application Frontiers

Jingyan Wang, Yang Zhao, Haotian Mao, Xubo Yang

专题命中 记忆与上下文管理 :agent(abstract)

Comments Withdrawn by the authors after identifying improper reuse of illustrative materials and partial omission of citations in certain sections. A revised version will be prepared to ensure accurate attribution, and comprehensive citation coverage

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.09099 2025-10-13 cond-mat.soft 50%

Active Rosensweig Patterns

Carlo Rigoni, Max Philipp Holl, Alberto Scacchi, Emil Stråka, Fereshteh Sohrabi, Mikko P. Haataja, Maria Sammalkorpi, Jaakko V. I. Timonen

专题命中 记忆与上下文管理 :agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏