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 4758 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 记忆与上下文管理 4758 篇

2603.10747 2026-03-12 cs.DB 82%

Pneuma-Seeker: A Relational Reification Mechanism to Align AI Agents with Human Work over Relational Data

Pneuma-Seeker: 一种关系重构机制,用于将AI代理与关系数据上的人类工作对齐

Muhammad Imam Luthfi Balaka, John Hillesland, Kemal Badur, Raul Castro Fernandez

专题命中 记忆与上下文管理 :AI agent(title);planning(abstract);agentic(abstract)

AI总结 Pneuma-Seeker通过关系重构机制,将AI代理与人类工作对齐,提升数据处理的准确性和可信赖性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.08812 2026-03-11 cs.CV 82%

VisionCreator-R1: A Reflection-Enhanced Native Visual-Generation Agentic Model

VisionCreator-R1: 一种增强反思的原生视觉生成代理模型

Jinxiang Lai, Wenzhe Zhao, Zexin Lu, Hualei Zhang, Qinyu Yang, Rongwei Quan, Zhimin Li, Shuai Shao, Song Guo, Qinglin Lu

机构 * Tencent Hunyuan(腾讯文言) Hong Kong University of Science and Technology(香港科学与技术大学)

专题命中 记忆与上下文管理 :agentic(title);agent(abstract);planning(abstract)

AI总结 VisionCreator-R1通过引入反射-计划联合优化方法,提升视觉生成代理在单图和多图任务中的表现,优于现有模型。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.08745 2026-03-11 cs.AR cs.MA cs.PF 82%

ChatNeuroSim: An LLM Agent Framework for Automated Compute-in-Memory Accelerator Deployment and Optimization

ChatNeuroSim:一种用于自动计算在内存加速器部署和优化的LLM代理框架

Ming-Yen Lee, Shimeng Yu

专题命中 记忆与上下文管理 :agent(title,abstract);workflow(abstract)

AI总结 ChatNeuroSim是一种基于LLM的代理框架,用于自动部署和优化计算在内存加速器,通过设计空间修剪技术提升优化效率。

Comments 30 pages, 16 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.05873 2026-03-09 cs.CV 82%

Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentation

从权重空间到记忆空间的迁移适应:一种用于医学图像分割的记忆增强代理

Bowen Chen, Qiaohui Gao, Shaowen Wan, Shanhui Sun, Wei Liu, Xiang Li, Tianming Liu, Lin Zhao

机构 * Department of Electrical and Computer Engineering, University of California, Santa Barbara, Santa Barbara, CA 93106, USA(电子工程系,加州大学圣芭芭拉分校) College of Engineering, Northeastern University, Boston, MA 02115, USA(工程学院,东北大学) Department of Biomedical Engineering, New Jersey Institute of Technology, Newark, NJ 07102, USA(生物医学工程系,新泽西理工学院) United Imaging Intelligence, Burlington, MA 01803, USA(联合影像智能公司) Department of Radiation Oncology, Mayo Clinic, Scottsdale, AZ 85259, USA(放射肿瘤科,梅奥诊所) Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA 02115, USA(放射科,麻省总医院和哈佛医学院) School of Computing, University of Georgia, Athens, GA 30602, USA(计算学院,佐治亚大学)

专题命中 记忆与上下文管理 :agent(title,abstract);agentic(abstract)

AI总结 本文提出MemSeg-Agent,通过将适应从权重空间转移到记忆空间,实现少样本学习、联邦监督学习和测试时间适应,提升医学图像分割的泛化能力和效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2603.05484 2026-03-06 cs.CV 82%

Towards Multimodal Lifelong Understanding: A Dataset and Agentic Baseline

迈向多模态终身理解:一个数据集和代理基准

Guo Chen, Lidong Lu, Yicheng Liu, Liangrui Dong, Lidong Zou, Jixin Lv, Zhenquan Li, Xinyi Mao, Baoqi Pei, Shihao Wang, Zhiqi Li, Karan Sapra, Fuxiao Liu, Yin-Dong Zheng, Yifei Huang, Limin Wang, Zhiding Yu, Andrew Tao, Guilin Liu, Tong Lu

专题命中 记忆与上下文管理 :agentic(title,abstract);agent(abstract)

AI总结 本文提出MM-Lifelong数据集和ReMA代理,解决多模态终身理解中的工作记忆瓶颈和全局定位崩溃问题,通过动态内存管理提升模型性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.07667 2026-03-03 econ.EM stat.AP stat.ML 82%

Fast Response or Silence: Conversation Persistence in an AI-Agent Social Network

快速响应还是沉默:AI代理社交网络中的对话持续性

Aysajan Eziz

专题命中 记忆与上下文管理 :agent(title,abstract);AI agent(abstract)

AI总结 Moltbook上的AI代理社交互动表现为快速响应或沉默,缺乏长期持续的多步骤协调。

Comments 32 pages, 6 figures, 18 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.08369 2026-02-10 cs.AI cs.CL cs.LG 82%

MemAdapter: Fast Alignment across Agent Memory Paradigms via Generative Subgraph Retrieval

MemAdapter:通过生成子图检索实现跨代理记忆范式的快速对齐

Xin Zhang, Kailai Yang, Chenyue Li, Hao Li, Qiyu Wei, Jun'ichi Tsujii, Sophia Ananiadou

机构 * The University of Manchester(曼彻斯特大学) Stanford University(斯坦福大学) Imperial College London(伦敦帝国理工学院) National Institute of Advanced Industrial Science(国家先进工业科学与技术研究院)

专题命中 记忆与上下文管理 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

AI总结 MemAdapter通过生成子图检索实现跨代理记忆范式的快速对齐,提升记忆检索灵活性并降低对齐成本,实验显示其性能优于现有系统。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.22705 2026-02-02 cs.DC 82%

CONCUR: High-Throughput Agentic Batch Inference of LLM via Congestion-Based Concurrency Control

CONCUR: 通过基于拥堵的并发控制实现LLM的高吞吐量代理批推断

Qiaoling Chen, Zhisheng Ye, Tian Tang, Peng Sun, Boyu Tian, Guoteng Wang, Shenggui Li, Yonggang Wen, Zhenhua Han, Tianwei Zhang

专题命中 记忆与上下文管理 :agentic(title,abstract);agent(abstract)

AI总结 CONCUR通过基于拥堵的并发控制,有效缓解LLM批推断中的中间阶段抖动问题,提升吞吐量达4.09倍。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20986 2025-12-25 cs.CR 82%

AegisAgent: An Autonomous Defense Agent Against Prompt Injection Attacks in LLM-HARs

AegisAgent:一种对抗LLM-HAR中提示注入攻击的自主防御代理

Yihan Wang, Huanqi Yang, Shantanu Pal, Weitao Xu

专题命中 记忆与上下文管理 :agent(title,abstract);autonomous agent(abstract)

AI总结 AegisAgent通过自主推理和验证机制,有效降低LLM-HAR系统中提示注入攻击的成功率,提升系统安全性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22732 2025-12-23 cs.LG cs.AI cs.CL cs.IR cs.MA cs.RO 82%

WebATLAS: An LLM Agent with Experience-Driven Memory and Action Simulation

WebATLAS: 一种基于经验驱动记忆和动作模拟的LLM代理

Jiali Cheng, Anjishnu Kumar, Roshan Lal, Rishi Rajasekaran, Hani Ramezani, Omar Zia Khan, Oleg Rokhlenko, Sunny Chiu-Webster, Gang Hua, Hadi Amiri

机构 * University of Massachusetts Lowell(马萨诸塞大学洛威尔分校) Amazon Alexa AI(亚马逊Alexa人工智能)

专题命中 记忆与上下文管理 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

AI总结 WebATLAS通过经验驱动的记忆和前瞻动作模拟,实现无需微调的自主网页导航,成功率达63%。

Comments 9 pages, NeurIPS 2025 Workshop on Language Agents and World Models

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.12818 2025-12-16 cs.CL cs.AI cs.IR cs.LG 82%

Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects

事后诸葛亮:构建具有保留、回忆和反思能力的智能体记忆

Chris Latimer, Nicoló Boschi, Andrew Neeser, Chris Bartholomew, Gaurav Srivastava, Xuan Wang, Naren Ramakrishnan

机构 * The Washington Post(华盛顿邮报) Virginia Tech(弗吉尼亚理工大学)

专题命中 记忆与上下文管理 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

AI总结 Hindsight通过结构化内存架构提升智能体在长对话中的记忆与推理能力,显著提高多会话和开放领域问题的准确率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.26386 2025-10-29 cs.CV 82%

PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer

Zhiwei Yang, Chen Gao, Mike Zheng Shou

机构 * Xidian University(西安电子科技大学) Show Lab, National University of Singapore(新加坡国立大学Show实验室)

专题命中 记忆与上下文管理 :agentic(title,abstract);planning(abstract)

Comments Accepted by NeurIPS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.09038 2025-10-13 cs.AI cs.CL cs.CV cs.CY cs.LG 82%

Auto-scaling Continuous Memory for GUI Agent

Wenyi Wu, Kun Zhou, Ruoxin Yuan, Vivian Yu, Stephen Wang, Zhiting Hu, Biwei Huang

机构 * University of California, San Diego(加州大学圣地亚哥分校) Fudan University(复旦大学) Abel AI

专题命中 记忆与上下文管理 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.21301 2025-09-26 cs.OS 82%

Nova: Real-Time Agentic Vision-Language Model Serving with Adaptive Cross-Stage Parallelization

Yuhang Xu, Shengzhong Liu, Dong Zhang, Bingheng Yan, Fan Wu, Guihai Chen

专题命中 记忆与上下文管理 :agentic(title,abstract);agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.19504 2025-08-28 cs.MA cs.DC 82%

Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents

Kevin Song, Anand Jayarajan, Yaoyao Ding, Qidong Su, Zhanda Zhu, Sihang Liu, Gennady Pekhimenko

专题命中 记忆与上下文管理 :agent(title,abstract);agentic(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.06605 2025-07-23 cs.RO 82%

Growing Trees with an Agent: Accelerating RRTs with Learned, Multi-Step Episodic Exploration

Xinyu Wu

专题命中 记忆与上下文管理 :agent(title,abstract);planning(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.17419 2025-06-24 cs.CL cs.AI cs.LG stat.ML 82%

UProp: Investigating the Uncertainty Propagation of LLMs in Multi-Step Agentic Decision-Making

Jinhao Duan, James Diffenderfer, Sandeep Madireddy, Tianlong Chen, Bhavya Kailkhura, Kaidi Xu

机构 * Drexel University(德雷塞尔大学) Lawrence Livermore National Laboratory(劳伦斯利弗莫尔国家实验室) Argonne National Laboratory(阿贡国家实验室) UNC Chapel Hill(北卡罗来纳大学教堂山分校)

专题命中 记忆与上下文管理 :agentic(title,abstract);分类 cs.AI、cs.CL、cs.LG

Comments 19 pages, 5 figures, 4 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.05388 2024-12-10 cs.CL cs.AI cs.LG 82%

CALICO: Conversational Agent Localization via Synthetic Data Generation

Andy Rosenbaum, Pegah Kharazmi, Ershad Banijamali, Lu Zeng, Christopher DiPersio, Pan Wei, Gokmen Oz, Clement Chung, Karolina Owczarzak, Fabian Triefenbach, Wael Hamza

专题命中 记忆与上下文管理 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

Comments Accepted to The 37th International Conference on Neural Information Processing Systems (NeurIPS 2023) December 10-16, 2023 - SyntheticData4ML Workshop, New Orleans, United States https://neurips.cc/virtual/2023/workshop/66540

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.03624 2024-12-06 cs.AI cs.CL cs.LG cs.MA stat.ML 82%

How to Correctly do Semantic Backpropagation on Language-based Agentic Systems

Wenyi Wang, Hisham A. Alyahya, Dylan R. Ashley, Oleg Serikov, Dmitrii Khizbullin, Francesco Faccio, Jürgen Schmidhuber

专题命中 记忆与上下文管理 :agentic(title,abstract);分类 cs.AI、cs.CL、cs.LG

Comments 11 pages in main text + 2 pages of references + 15 pages of appendices, 2 figures in main text + 17 figures in appendices, 2 tables in main text + 1 table in appendices, 2 algorithms in main text; source code available at https://github.com/HishamAlyahya/semantic_backprop

详情

展开后加载摘要…

URL PDF HTML 收藏
2409.07714 2024-11-06 cs.CV cs.MA 82%

CollaMamba: Efficient Collaborative Perception with Cross-Agent Spatial-Temporal State Space Model

Yang Li, Quan Yuan, Guiyang Luo, Xiaoyuan Fu, Xuanhan Zhu, Yujia Yang, Rui Pan, Jinglin Li

专题命中 记忆与上下文管理 :agent(title,abstract);multi-agent(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.14744 2024-10-29 cs.AI cs.CL cs.CY cs.LG 82%

Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation

Jiawei Wang, Renhe Jiang, Chuang Yang, Zengqing Wu, Makoto Onizuka, Ryosuke Shibasaki, Noboru Koshizuka, Chuan Xiao

专题命中 记忆与上下文管理 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

Comments NeurIPS 2024. Source codes are available at https://github.com/Wangjw6/LLMob/

详情

展开后加载摘要…

URL PDF HTML 收藏
2403.11481 2024-07-16 cs.CV 82%

VideoAgent: A Memory-augmented Multimodal Agent for Video Understanding

Yue Fan, Xiaojian Ma, Rujie Wu, Yuntao Du, Jiaqi Li, Zhi Gao, Qing Li

专题命中 记忆与上下文管理 :agent(title,abstract);tool-use(abstract)

Comments ECCV-24; Project page: videoagent.github.io; First two authors contributed equally

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.11247 2024-06-18 cs.CV 82%

STEVE Series: Step-by-Step Construction of Agent Systems in Minecraft

Zhonghan Zhao, Wenhao Chai, Xuan Wang, Ke Ma, Kewei Chen, Dongxu Guo, Tian Ye, Yanting Zhang, Hongwei Wang, Gaoang Wang

专题命中 记忆与上下文管理 :agent(title,abstract);multi-agent(abstract)

Comments CVPR 2024 Embodied AI Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2406.05872 2024-06-11 cs.LG cs.AI cs.CL 82%

STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models

Shreyas Basavatia, Keerthiram Murugesan, Shivam Ratnakar

专题命中 记忆与上下文管理 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

Comments ACL 2024 (Findings)

详情

展开后加载摘要…

URL PDF HTML 收藏
2310.10134 2023-10-17 cs.CL cs.AI cs.LG 82%

CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalization

Bodhisattwa Prasad Majumder, Bhavana Dalvi Mishra, Peter Jansen, Oyvind Tafjord, Niket Tandon, Li Zhang, Chris Callison-Burch, Peter Clark

专题命中 记忆与上下文管理 :agent(title,abstract);分类 cs.AI、cs.CL、cs.LG

Comments Project page: https://allenai.github.io/clin/

详情

展开后加载摘要…

URL PDF HTML 收藏
2210.06955 2022-10-14 cs.MA 82%

Agent-Based Modelling for Urban Analytics: State of the Art and Challenges

Nick Malleson, Mark Birkin, Daniel Birks, Jiaqi Ge, Alison Heppenstall, Ed Manley, Josie McCulloch, Patricia Ternes

专题命中 记忆与上下文管理 :agent(title,abstract);multi-agent(abstract)

Journal ref AI Communications 35, 393--406 (2022)

详情

展开后加载摘要…

URL PDF HTML 收藏
1812.08014 2018-12-20 cs.CR 82%

Intelligent Autonomous Agents are Key to Cyber Defense of the Future Army Networks

Alexander Kott

专题命中 记忆与上下文管理 :autonomous agent(title,abstract);agent(abstract)

Comments This is a pre-print version of the article appearing in The Cyber Defense Review journal, Fall 2018. arXiv admin note: text overlap with arXiv:1803.11256

详情

展开后加载摘要…

URL PDF HTML 收藏
2402.09727 2024-07-23 cs.CL cs.AI cs.IR 82%

A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts

Kuang-Huei Lee, Xinyun Chen, Hiroki Furuta, John Canny, Ian Fischer

专题命中 记忆与上下文管理 :agent(title,abstract);分类 cs.AI、cs.CL

Comments Website: https://read-agent.github.io

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.17684 2026-08-19 cs.AI 新提交 81%

Auditing Self-Evolution in Financial Agents: Capability Gains, Security Drift, and Execution-Interface Mismatch

金融智能体的自我进化审计:能力提升、安全漂移与执行接口不匹配

Jialong Li, Jialing Zhu

专题命中 记忆与上下文管理 :agent(abstract,abstract_cn);workflow(abstract,abstract_cn);分类 cs.AI

AI总结 该研究通过模拟电子银行环境审计SkillOpt、AWM、ReasoningBank等自我进化金融智能体,发现仅靠准确率评估不足,需跟踪退化、攻击面接触等指标,且AWM存在执行接口不匹配的评估风险。

Comments 8 pages, 2 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.23942 2026-07-28 cs.AI 新提交 81%

From Cognitive Architectures to Language Agents: A Mechanism-Level Review of Lineage, Convergence, and Migration Gaps

从认知架构到语言智能体:谱系、融合与迁移差距的机制层面综述

Haodi Fan, Zucong Lan

专题命中 记忆与上下文管理 :agent(abstract);tool use(abstract);planning(abstract);workflow(abstract)

AI总结 该综述连接多个认知架构与语言智能体系统,重构机制并编码相关关系,指出现代智能体部分功能已实现,最强机会在机制耦合,存在五个剩余组合,贡献了机制目录、证据深度框架及可证伪议程。

Comments 28 pages, 9 figures, 14 tables. Review article

详情

展开后加载摘要…

URL PDF HTML 收藏