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 5059 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 工具调用 5059 篇

2511.20349 2025-11-26 cs.LG 57%

Complexity Reduction Study Based on RD Costs Approximation for VVC Intra Partitioning

基于RD成本近似用于VVC内划分的复杂度降低研究

M. E. A. Kherchouche, F. Galpin, T. Dumas, F. Schnitzler, D. Menard, L. Zhang

机构 * InterDigital, R&I(InterDigital研发与创新部) Univ Rennes, INSA Rennes(里昂大学,印斯那学院) CNRS, IETR - UMR 6164(国家科学研究中心,IETR研究所)

专题命中 工具调用 :agent(abstract);分类 cs.LG

AI总结 本文提出两种基于机器学习的VVC内划分复杂度降低方法,通过回归和强化学习技术优化RD成本预测,提升RDO过程效率。

Comments 2025 Data Compression Conference (DCC)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.19830 2025-11-26 cs.DB cs.AI 57%

Beyond Relational: Semantic-Aware Multi-Modal Analytics with LLM-Native Query Optimization

超越关系:基于语义的多模态分析与LLM原生查询优化

Junhao Zhu, Lu Chen, Xiangyu Ke, Ziquan Fang, Tianyi Li, Yunjun Gao, Christian S. Jensen

机构 * Zhejiang University(浙江大学) Aalborg University(奥胡斯大学)

专题命中 工具调用 :agentic(abstract);分类 cs.AI

AI总结 Nirvana通过结合可编程语义运算符和LLM原生查询优化,实现多模态数据分析,显著提升效率和可扩展性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04042 2025-11-26 cs.RO cs.AI 57%

An LLM-based Framework for Human-Swarm Teaming Cognition in Disaster Search and Rescue

基于大语言模型的灾难搜索救援中人-群智能协同认知框架

Kailun Ji, Xiaoyu Hu, Xinyu Zhang, Jun Chen

机构 * School of Electronics and Information, Northwestern Polytechnical University(电子工程学院,西北工业大学) Chongqing Institute for Brain and Intelligence, Guangyang Bay Laboratory(脑科学与智能研究院,广阳湾实验室)

专题命中 工具调用 :planning(abstract);分类 cs.AI

AI总结 本文提出基于大语言模型的LLM-CRF系统,通过自然交互捕捉意图并实现任务规划,显著提升灾难救援任务效率与成功率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.18035 2025-11-25 stat.ME cs.LG stat.CO stat.ML 57%

On a Reinforcement Learning Methodology for Epidemic Control, with application to COVID-19

关于流行病控制的强化学习方法论,应用于新冠疫情

Giacomo Iannucci, Petros Barmpounakis, Alexandros Beskos, Nikolaos Demiris

专题命中 工具调用 :agent(abstract);分类 cs.LG

AI总结 本文提出了一种结合贝叶斯推断与强化学习的流行病控制方法,通过实时数据驱动决策,有效降低ICU负担,应用于新冠疫情控制。

Comments Submitted to Statistics and Computing. Approx. 26 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23662 2025-11-24 cs.CL 57%

ToolHaystack: Stress-Testing Tool-Augmented Language Models in Realistic Long-Term Interactions

ToolHaystack: 在现实长期交互中压力测试工具增强的语言模型

Beong-woo Kwak, Minju Kim, Dongha Lim, Hyungjoo Chae, Dongjin Kang, Sunghwan Kim, Dongil Yang, Jinyoung Yeo

机构 * Department of Artificial Intelligence, Yonsei University(人工智能系,延世大学) Department of Computer Science & Engineering, Yonsei University(计算机科学与工程系,延世大学)

专题命中 工具调用 :tool use(abstract);分类 cs.CL

AI总结 ToolHaystack通过模拟现实长期交互中的噪声和上下文干扰,揭示了现有工具增强语言模型在长期鲁棒性方面的不足。

Comments Our code and data are available at https://github.com/bwookwak/ToolHaystack Edited for adding acknowledgement section

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16278 2025-11-21 cs.CR cs.AI 57%

"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios

为生存,我必须背叛:通过博弈论场景进行大语言模型的劫持攻击

Zhen Sun, Zongmin Zhang, Deqi Liang, Han Sun, Yule Liu, Yun Shen, Xiangshan Gao, Yilong Yang, Shuai Liu, Yutao Yue, Xinlei He

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)) East China Normal University(华东师范大学) Flexera(Flexera公司) Zhejiang University(浙江大学) Xidian University(西安电子科技大学) Xi’an Jiaotong University(西安交通大学) Institute of Deep Perception Technology, JITRI(JITRI深度感知技术研究所)

专题命中 工具调用 :agent(abstract);分类 cs.AI

AI总结 本文提出一种基于博弈论的可扩展黑盒劫持框架GTA,通过重塑LLM目标以提高攻击成功率,实现在多种场景下的高ASR表现。

Comments 20 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.11677 2025-11-18 cs.LG q-fin.GN 57%

Instruction Tuning Chronologically Consistent Language Models

Songrun He, Linying Lv, Asaf Manela, Jimmy Wu

机构 * Washington University in St. Louis(华盛顿大学圣路易斯分校)

专题命中 工具调用 :tool use(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.10071 2025-11-18 cs.AI 57%

Advanced Tool Learning and Selection System (ATLASS): A Closed-Loop Framework Using LLM

Mohd Ariful Haque, Justin Williams, Sunzida Siddique, Md. Hujaifa Islam, Hasmot Ali, Kishor Datta Gupta, Roy George

机构 * Clark Atlanta University(克拉克亚特兰大大学) Daffodil International University(达福尔国际大学) Ahsanullah University of Science and Technology(阿沙努拉大学科学与技术学院)

专题命中 工具调用 :agent(abstract);分类 cs.AI

Journal ref 2025 IEEE International Conference on Service-Oriented System Engineering (SOSE), Tucson, AZ, USA, 21-24 July 2025, IEEE

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.12159 2025-11-18 cs.CL 57%

CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic

Yaocheng Zhang, Haohuan Huang, Zijun Song, Yuanheng Zhu, Qichao Zhang, Zijie Zhao, Dongbin Zhao

机构 * Institute of Automation, CAS(中国科学院自动化研究所) School of Advanced Interdisciplinary Sciences, UCAS(清华大学交叉信息学院) School of Artificial Intelligence, UCAS(清华大学人工智能学院)

专题命中 工具调用 :agent(abstract);分类 cs.CL

Comments 17 pages, 10 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.04339 2025-11-17 math.ST cond-mat.dis-nn cs.IT cs.LG math.IT math.PR stat.TH 57%

Analysis of Diffusion Models for Manifold Data

Anand Jerry George, Rodrigo Veiga, Nicolas Macris

机构 * EPFL, School of Computer and Communication Sciences(苏黎世联邦理工学院计算机与通信科学学院) Department of Electrical Engineering University 1 City 1(电气工程系大学1城市1)

专题命中 工具调用 :tool use(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09820 2025-11-14 cs.CV cs.AI 57%

From Street to Orbit: Training-Free Cross-View Retrieval via Location Semantics and LLM Guidance

Jeongho Min, Dongyoung Kim, Jaehyup Lee

专题命中 工具调用 :planning(abstract);分类 cs.AI

Comments Accepted to WACV 2026, 10pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.12211 2025-11-14 cs.RO cs.AI 57%

Improving Pre-Trained Vision-Language-Action Policies with Model-Based Search

Cyrus Neary, Omar G. Younis, Artur Kuramshin, Ozgur Aslan, Glen Berseth

机构 * Mila — Quebec AI Institute(魁北克人工智能研究所) Université de Montréal(蒙特利尔大学) The University of British Columbia(不列颠哥伦比亚大学)

专题命中 工具调用 :planning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.09549 2025-11-13 cs.AI 57%

Breadth-First Search vs. Restarting Random Walks for Escaping Uninformed Heuristic Regions

Daniel Platnick, Dawson Tomasz, Eamon Earl, Sourena Khanzadeh, Richard Valenzano

机构 * Toronto Metropolitan University(多伦多 Metropolitan 大学)

专题命中 工具调用 :planning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.24197 2025-11-13 cs.AI 57%

Learning API Functionality from In-Context Demonstrations for Tool-based Agents

Bhrij Patel, Ashish Jagmohan, Aditya Vempaty

机构 * University of Maryland, College Park(马里兰大学学院公园分校) Emergence AI NYC(纽约Emergence AI)

专题命中 工具调用 :agent(abstract);分类 cs.AI

Comments 19 Pages, 14 Figures, 7 Tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.07709 2025-11-12 cs.SE 57%

Post Processing Graphical User Interface for Heat Flow Visualization

Lars Olt, Luis Diego Fonseca Flores, Ian Mckinley

专题命中 工具调用 :tool use(abstract);分类 cs.SE

Comments Presented at the 53rd International Conference on Environmental Systems (ICES 2024), Louisville, Kentucky, USA, 2024. Official link: https://hdl.handle.net/2346/98969

Journal ref Proceedings of the 53rd International Conference on Environmental Systems, 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.16309 2025-11-11 physics.med-ph cs.AI 57%

Evaluating The Performance of Using Large Language Models to Automate Summarization of CT Simulation Orders in Radiation Oncology

Meiyun Cao, Shaw Hu, Jason Sharp, Edward Clouser, Jason Holmes, Linda L. Lam, Xiaoning Ding, Diego Santos Toesca, Wendy S. Lindholm, Samir H. Patel, Sujay A. Vora, Peilong Wang, Wei Liu

机构 * Department of Radiation Oncology, Mayo Clinic, Phoenix, AZ 85054(放射肿瘤科,梅奥诊所,凤凰城,AZ 85054)

专题命中 工具调用 :workflow(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.04137 2025-11-07 cs.CV cs.AI 57%

Learning from Online Videos at Inference Time for Computer-Use Agents

Yujian Liu, Ze Wang, Hao Chen, Ximeng Sun, Xiaodong Yu, Jialian Wu, Jiang Liu, Emad Barsoum, Zicheng Liu, Shiyu Chang

机构 * UC Santa Barbara(UC圣芭芭拉大学) Advanced Micro Devices, Inc.(先进微器件公司)

专题命中 工具调用 :agent(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.27206 2025-11-03 cs.AI 57%

Fints: Efficient Inference-Time Personalization for LLMs with Fine-Grained Instance-Tailored Steering

Kounianhua Du, Jianxing Liu, Kangning Zhang, Wenxiang Jiao, Yuan Lu, Jiarui Jin, Weiwen Liu, Yong Yu, Weinan Zhang

机构 * Shanghai Jiao Tong University(上海交通大学) Xiaohongshu Inc.(小红书公司)

专题命中 工具调用 :function calling(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2407.11873 2025-10-31 stat.ML cs.LG math.PR 57%

Infinite-dimensional Mahalanobis Distance with Applications to Kernelized Novelty Detection

Nikita Zozoulenko, Thomas Cass, Lukas Gonon

专题命中 工具调用 :tool use(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.25504 2025-10-30 cs.AI 57%

Multi-Objective Search: Algorithms, Applications, and Emerging Directions

Oren Salzman, Carlos Hernández Ulloa, Ariel Felner, Sven Koenig

专题命中 工具调用 :planning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.24551 2025-10-29 cs.AI 57%

Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives

Gang Chen, Changshuo Liu, Gene Anne Ooi, Marcus Tan, Zhongle Xie, Jianwei Yin, James Wei Luen Yip, Wenqiao Zhang, Jiaqi Zhu, Beng Chin Ooi

机构 * College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China(浙江大学计算机科学与技术学院) College of Software Technology, Zhejiang University, Ningbo 315100, China(浙江大学软件技术学院) School of Computing, National University of Singapore, Singapore 117417(新加坡国立大学计算机学院) Singapore General Hospital, Singapore 169608(新加坡中央医院) National University Hospital, Singapore 119074(新加坡国立医院)

专题命中 工具调用 :agentic(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.24051 2025-10-29 cs.CL 57%

Pie: A Programmable Serving System for Emerging LLM Applications

In Gim, Zhiyao Ma, Seung-seob Lee, Lin Zhong

机构 * Yale University(耶鲁大学)

专题命中 工具调用 :agentic(abstract);分类 cs.CL

Comments SOSP 2025. Source code available at https://github.com/pie-project/pie

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.23691 2025-10-29 cs.AI 57%

Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents

Zihao Wang, Xujing Li, Yining Ye, Junjie Fang, Haoming Wang, Longxiang Liu, Shihao Liang, Junting Lu, Zhiyong Wu, Jiazhan Feng, Wanjun Zhong, Zili Li, Yu Wang, Yu Miao, Bo Zhou, Yuanfan Li, Hao Wang, Zhongkai Zhao, Faming Wu, Zhengxuan Jiang, Weihao Tan, Heyuan Yao, Shi Yan, Xiangyang Li, Yitao Liang, Yujia Qin, Guang Shi

机构 * Bytedance Seed(字节跳动种子)

专题命中 工具调用 :agent(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22632 2025-10-28 cs.GR cs.LG 57%

Environment-aware Motion Matching

Jose Luis Ponton, Sheldon Andrews, Carlos Andujar, Nuria Pelechano

机构 * Universitat Politècnica de Catalunya(巴塞罗那理工大学) École de technologie supérieure (ÉTS)(高级技术学院)

专题命中 工具调用 :planning(abstract);分类 cs.LG

Comments Published in ACM TOG and presented in SIGGRAPH ASIA 2025. Project webpage: https://upc-virvig.github.io/Environment-aware-Motion-Matching/

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.05294 2025-10-27 cs.LG 57%

A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search

Arnav Kumar Jain, Vibhakar Mohta, Subin Kim, Atiksh Bhardwaj, Juntao Ren, Yunhai Feng, Sanjiban Choudhury, Gokul Swamy

机构 * Mila- Quebec AI Institute(蒙特利尔AI研究所) Université de Montréal(蒙特利尔大学) Carnegie Mellon University(卡内基梅隆大学) Cornell University(康奈尔大学)

专题命中 工具调用 :agent(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.19872 2025-10-24 cs.LG 57%

An Integrated Approach to Neural Architecture Search for Deep Q-Networks

Iman Rahmani, Saman Yazdannik, Morteza Tayefi, Jafar Roshanian

机构 * Iman Rahmani Intelligent Control Systems Institute (ICSI) Department of Aerospace Engineering K. N. Toosi University of Technology Tehran, Iran(智能控制系统研究所(ICSI)航空航天工程系,K.N.托菲大学技术学院,泰赫兰,伊朗) Saman Yazdannik Machine Learning Engineer Isfahan Chamber of Commerce, Industries, Mines and Agriculture (ECCIMA) Isfahan, Iran(机器学习工程师,以沙万商会、工业、采矿和农业(ECCIMA)) Morteza Tayefi Department of Aerospace Engineering K. N. Toosi University of Technology Tehran, Iran(航空航天工程系,K.N.托菲大学技术学院,泰赫兰,伊朗) Jafar Roshanian Intelligent Control Systems Institute (ICSI) Department of Aerospace Engineering K. N. Toosi University of Technology Tehran, Iran(智能控制系统研究所(ICSI)航空航天工程系,K.N.托菲大学技术学院,泰赫兰,伊朗)

专题命中 工具调用 :agent(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.18229 2025-10-21 econ.GN cs.AI q-fin.EC 57%

From Individual Learning to Market Equilibrium: Correcting Structural and Parametric Biases in RL Simulations of Economic Models

Ruxin Chen, Zeqiang Zhang

机构 * Department of Economics, Nagoya University(名古屋大学经济学系) Institute of Neural Information Processing, Ulm University(乌尔姆大学神经信息处理研究所)

专题命中 工具调用 :agent(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14727 2025-10-17 cs.LG 57%

The Pursuit of Diversity: Multi-Objective Testing of Deep Reinforcement Learning Agents

Antony Bartlett, Cynthia Liem, Annibale Panichella

机构 * Delft University of Technology(代尔夫特理工大学)

专题命中 工具调用 :agent(abstract);分类 cs.LG

Comments Pre-print - Accepted at Symposium on Search Based Software Engineering (SSBSE) 2025 co-located with ASE'25

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.12080 2025-10-15 cs.AI 57%

Evaluating the Quality of Randomness and Entropy in Tasks Supported by Large Language Models

Rabimba Karanjai, Yang Lu, Ranjith Chodavarapu, Lei Xu, Weidong Shi

机构 * University Of Houston(休斯敦大学) Kent State University(肯特州立大学)

专题命中 工具调用 :AI agent(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.08276 2025-10-10 cs.CL 57%

Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window

Qiaoyu Tang, Hao Xiang, Le Yu, Bowen Yu, Yaojie Lu, Xianpei Han, Le Sun, WenJuan Zhang, Pengbo Wang, Shixuan Liu, Zhenru Zhang, Jianhong Tu, Hongyu Lin, Junyang Lin

机构 * Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所信息处理实验室) Alibaba Group(阿里巴巴集团) University of Chinese Academy of Sciences(中国科学院大学)

专题命中 工具调用 :agent(abstract);分类 cs.CL

详情

展开后加载摘要…

URL PDF HTML 收藏