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 4737 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 记忆与上下文管理 4737 篇

2601.05107 2026-01-09 cs.AI 79%

Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction

可控的记忆使用:在长期人机交互中平衡锚定与创新

Muzhao Tian, Zisu Huang, Xiaohua Wang, Jingwen Xu, Zhengkang Guo, Qi Qian, Yuanzhe Shen, Kaitao Song, Jiakang Yuan, Changze Lv, Xiaoqing Zheng

机构 * College of Computer Science and Artificial Intelligence, Fudan University(计算机科学与人工智能学院,复旦大学)

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

AI总结 SteeM通过动态调节记忆依赖程度,在长期人机交互中平衡锚定与创新,提升个性化协作效果。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.21567 2025-12-29 cs.CL 79%

Beyond Heuristics: A Decision-Theoretic Framework for Agent Memory Management

超越启发法:一个决策理论框架用于智能体记忆管理

Changzhi Sun, Xiangyu Chen, Jixiang Luo, Dell Zhang, Xuelong Li

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

AI总结 本文提出DAM框架,通过决策理论方法解决智能体记忆管理问题,强调长期效用与风险评估,为不确定性下的记忆系统研究奠定基础。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.08151 2025-12-24 cs.AI 79%

Trust Semantics Distillation for Collaborator Selection via Memory-Augmented Agentic AI

基于记忆增强代理AI的信任语义蒸馏用于协作者选择

Botao Zhu, Jeslyn Wang, Dusit Niyato, Xianbin Wang

机构 * Western University(西方大学) University of Toronto(多伦多大学) Nanyang Technological University(南洋理工大学)

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

AI总结 本文提出基于记忆增强代理AI的任务特定信任语义蒸馏模型,通过教师-学生架构实现高效协作者选择,提升信任评估的准确性和效率。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.10218 2025-12-23 cs.SE 79%

Does SWE-Bench-Verified Test Agent Ability or Model Memory?

SWE-Bench-Verified测试的是代理能力还是模型记忆?

Thanosan Prathifkumar, Noble Saji Mathews, Meiyappan Nagappan

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

AI总结 研究发现SWE-Bench-Verified基准可能反映模型训练记忆而非真实问题解决能力,建议转向更注重污染控制的新数据集。

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.08139 2025-12-23 cs.IT cs.LG math.IT 79%

SCA-LLM: Spectral-Attentive LLM-Based Wireless World Modeling for Agentic Communications

SCA-LLM:基于频谱-注意力的LLM无线世界建模用于智能通信

Ke He, Le He, Lisheng Fan, Xianfu Lei, Thang X. Vu, George K. Karagiannidis, Symeon Chatzinotas

机构 * Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg(安全、可靠性与信任跨学科研究中心(SnT),卢森堡大学) School of Computer Science of Guangzhou University(广州大学计算机科学学院) School of Information Science and Technology, Institute of Mobile Communications, Southwest Jiaotong University(信息科学与技术学院,移动通信研究所,西南交通大学) Department of Electrical and Computer Engineering, Aristotle University of Thessaloniki(电气与计算机工程系,塞萨洛尼基阿瑞斯托大学) Cyber Security Systems and Applied AI Research Center, Lebanese American University (LAU)(网络安全与应用人工智能研究中心,黎巴嫩美国大学)

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

AI总结 SCA-LLM通过频谱-注意力适配器将信道状态信息与LLM结合,实现无线世界建模,提升预测性能和零样本泛化能力。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.06688 2025-12-09 cs.CL 79%

PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory

PersonaMem-v2:通过学习隐式用户人设和代理记忆实现个性化智能

Bowen Jiang, Yuan Yuan, Maohao Shen, Zhuoqun Hao, Zhangchen Xu, Zichen Chen, Ziyi Liu, Anvesh Rao Vijjini, Jiashu He, Hanchao Yu, Radha Poovendran, Gregory Wornell, Lyle Ungar, Dan Roth, Sihao Chen, Camillo Jose Taylor

机构 * University of Pennsylvania(宾夕法尼亚大学) Massachusetts Institute of Technology(麻省理工学院) University of Washington(华盛顿大学) University of California Santa Barbara(加州大学圣巴巴拉分校) Meta University of Southern California(南加州大学) University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校) Microsoft Corporation(微软公司)

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

AI总结 PersonaMem-v2通过学习隐式用户人设和代理记忆提升LLM个性化能力,实验显示强化微调使模型在隐式个性化任务中准确率达53%。

Comments Data is available at https://huggingface.co/datasets/bowen-upenn/PersonaMem-v2

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.06590 2025-12-09 cs.IR cs.AI cs.MA 79%

Towards Efficient Hypergraph and Multi-LLM Agent Recommender Systems

迈向高效超图和多LLM代理推荐系统

Tendai Mukande, Esraa Ali, Annalina Caputo, Ruihai Dong, Noel OConnor

机构 * Research Ireland ML-LABS Dublin City University(都柏林城市大学) ADAPT Centre(ADAPT中心) School of Computing(计算学院) Insight Research Ireland Centre for Data Analytics(Insight Research Ireland 数据分析中心) University College Dublin(都柏林大学)

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

AI总结 HGLMRec通过超图编码器和多LLM代理机制,提升推荐系统在计算效率和推荐质量上的表现。

Comments 8 Pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.13410 2025-11-27 cs.CL 79%

Mem-PAL: Towards Memory-based Personalized Dialogue Assistants for Long-term User-Agent Interaction

Mem-PAL: 向基于记忆的个性化对话助手迈进:长期用户-代理交互

Zhaopei Huang, Qifeng Dai, Guozheng Wu, Xiaopeng Wu, Kehan Chen, Chuan Yu, Xubin Li, Tiezheng Ge, Wenxuan Wang, Qin Jin

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

AI总结 Mem-PAL提出H$^2$Memory框架,通过合成数据和实验验证,提升长期用户-代理交互的个性化能力。

Comments Accepted by AAAI 2026 (Oral)

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.17315 2025-11-24 cs.CL 79%

Humanlike Multi-user Agent (HUMA): Designing a Deceptively Human AI Facilitator for Group Chats

人样多用户代理(HUMA):为群聊设计一种欺骗性人类AI助理工具

Mateusz Jacniacki, Martí Carmona Serrat

机构 * Soofte Research(Soofte研究机构)

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

AI总结 HUMA是一种基于LLM的多用户对话促进者,通过事件驱动架构模拟人类交互,实现在自然群聊中与人类相当的质量并难以识别。

Comments 9 pages, 4 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.06059 2025-11-18 cs.CR cs.CL 79%

Fact2Fiction: Targeted Poisoning Attack to Agentic Fact-checking System

Haorui He, Yupeng Li, Bin Benjamin Zhu, Dacheng Wen, Reynold Cheng, Francis C. M. Lau

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

Comments Accepted by AAAI 2026 (Oral). Code available at: https://trustworthycomp.github.io/Fact2Fiction/

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.27130 2025-11-03 cs.LG 79%

AI Agents in Drug Discovery

Srijit Seal, Dinh Long Huynh, Moudather Chelbi, Sara Khosravi, Ankur Kumar, Mattson Thieme, Isaac Wilks, Mark Davies, Jessica Mustali, Yannick Sun, Nick Edwards, Daniil Boiko, Andrei Tyrin, Douglas W. Selinger, Ayaan Parikh, Rahul Vijayan, Shoman Kasbekar, Dylan Reid, Andreas Bender, Ola Spjuth

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

Comments 45 pages, 12 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.23601 2025-10-28 cs.AI 79%

Alita-G: Self-Evolving Generative Agent for Agent Generation

Jiahao Qiu, Xuan Qi, Hongru Wang, Xinzhe Juan, Yimin Wang, Zelin Zhao, Jiayi Geng, Jiacheng Guo, Peihang Li, Jingzhe Shi, Shilong Liu, Mengdi Wang

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

Comments 15 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.20168 2025-10-24 cs.CL 79%

DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking

Tian Lan, Bin Zhu, Qianghuai Jia, Junyang Ren, Haijun Li, Longyue Wang, Zhao Xu, Weihua Luo, Kaifu Zhang

机构 * Alibaba International Digital Commerce(阿里巴巴国际数字商务)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.15261 2025-10-20 cs.AI 79%

AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory

Jitesh Jain, Shubham Maheshwari, Ning Yu, Wen-mei Hwu, Humphrey Shi

机构 * Adobe(Adobe公司) Netflix Eyeline Studios(Netflix Eyeline工作室) UIUC(伊利诺伊大学香槟分校)

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

Comments LAW 2025 Workshop at NeurIPS 2025. Work done from late 2023 to early 2024

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.14826 2025-10-17 cs.LG 79%

To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models

Eran Malach, Omid Saremi, Sinead Williamson, Arwen Bradley, Aryo Lotfi, Emmanuel Abbe, Josh Susskind, Etai Littwin

机构 * Apple(苹果公司)

专题命中 记忆与上下文管理 :tool-use(title);agentic(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.26200 2025-10-01 cs.NI cs.AI 79%

Toward an Unbiased Collective Memory for Efficient LLM-Based Agentic 6G Cross-Domain Management

Hatim Chergui, Miguel Catalan Cid, Pouria Sayyad Khodashenas, Daniel Camps Mur, Christos Verikoukis

机构 * i2CAT Foundation(i2CAT基金会) ISI/ATH University of Patras(帕特拉大学)

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

Comments 12 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.07815 2025-09-12 cs.RO cs.CV cs.LG 79%

Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Models

Seungjae Lee, Daniel Ekpo, Haowen Liu, Furong Huang, Abhinav Shrivastava, Jia-Bin Huang

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

Comments Project webpage: https://ive-robot.github.io/

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.21314 2025-09-04 cs.LG 79%

Convergence of regularized agent-state-based Q-learning in POMDPs

Amit Sinha, Matthieu Geist, Aditya Mahajan

机构 * Department of Electrical and Computer Engineering, McGill University(麦吉尔大学电气与计算机工程系) Earth Species Project(地球物种计划)

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

Comments Accepted in CDC 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.12630 2025-08-19 cs.CL 79%

Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational Context

Maitreyi Chatterjee, Devansh Agarwal

机构 * Cornell University(康奈尔大学)

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

Comments Paper is currently in peer review

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.09648 2025-08-14 cs.SE 79%

ReqInOne: A Large Language Model-Based Agent for Software Requirements Specification Generation

Taohong Zhu, Lucas C. Cordeiro, Youcheng Sun

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.13152 2025-07-01 cs.CV cs.AI 79%

Interpretable Interaction Modeling for Trajectory Prediction via Agent Selection and Physical Coefficient

Shiji Huang, Lei Ye, Min Chen, Wenhai Luo, Dihong Wang, Chenqi Xu, Deyuan Liang

机构 * College of Computer Science and Technology, Zhejiang University of Technology(计算机科学与技术学院,浙江工业大学)

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

Comments Accepted by International Conference on Intelligent Robots and Systems (IROS 2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.12497 2025-06-17 cs.AI 79%

Requirements for Recognition and Rapid Response to Unfamiliar Events Outside of Agent Design Scope

Robert E. Wray, Steven J. Jones, John E. Laird

机构 * Center for Integrated Cognition, IQMRI(整合认知中心,IQMRI)

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

Comments 10 pages + references, 3 figures. Accepted for AGI25 conference (oral presentation)

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.01718 2025-06-11 cs.LG q-bio.QM 79%

Learning surrogate equations for the analysis of an agent-based cancer model

Kevin Burrage, Pamela M. Burrage, Justin N. Kreikemeyer, Adelinde M. Uhrmacher, Hasitha N. Weerasinghe

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

Comments 13 pages, 7 figures; This version is identical to the one published at Frontiers

Journal ref Front. Appl. Math. Stat. Volume 11 (2025)

详情

展开后加载摘要…

URL PDF HTML 收藏
2502.13172 2025-06-04 cs.CR cs.AI 79%

Unveiling Privacy Risks in LLM Agent Memory

Bo Wang, Weiyi He, Shenglai Zeng, Zhen Xiang, Yue Xing, Jiliang Tang, Pengfei He

机构 * Michigan State University(密歇根州立大学) University of Georgia(佐治亚大学)

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

Comments ACL 2025 (Main Conference)

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.15928 2025-05-23 cs.CV cs.CL 79%

ViQAgent: Zero-Shot Video Question Answering via Agent with Open-Vocabulary Grounding Validation

Tony Montes, Fernando Lozano

机构 * The Department of Electrical and Electronics Engineering(电气与电子工程系) Universidad de los Andes(亚利桑德大学)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.20552 2025-04-30 cs.CL 79%

BrAIcht, a theatrical agent that speaks like Bertolt Brecht's characters

Baz Roland, Kristina Malyseva, Anna Pappa, Tristan Cazenave

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

Journal ref Generative Art Conference - GA2024, Generative Art and Design Lab, Argenia Association, Roma, Italy, Dec 2024, Venice, Italy. pp.290-296

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.02341 2025-04-15 cs.RO cs.AI 79%

UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility

Yonglin Tian, Fei Lin, Yiduo Li, Tengchao Zhang, Qiyao Zhang, Xuan Fu, Jun Huang, Xingyuan Dai, Yutong Wang, Chunwei Tian, Bai Li, Yisheng Lv, Levente Kovács, Fei-Yue Wang

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

Journal ref Information Fusion, Volume 122, 2025, 103158

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.07634 2025-04-11 cs.SE 79%

Agent That Debugs: Dynamic State-Guided Vulnerability Repair

Zhengyao Liu, Yunlong Ma, Jingxuan Xu, Junchen Ai, Xiang Gao, Hailong Sun, Abhik Roychoudhury

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.06681 2025-04-08 cs.AI cs.MA 79%

Toward LLM-Agent-Based Modeling of Transportation Systems: A Conceptual Framework

Tianming Liu, Jirong Yang, Yafeng Yin

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

Comments 39 pages; updated framework, literature review, and results

详情

展开后加载摘要…

URL PDF HTML 收藏
2504.01278 2025-04-03 cs.AI 79%

Strategize Globally, Adapt Locally: A Multi-Turn Red Teaming Agent with Dual-Level Learning

Si Chen, Xiao Yu, Ninareh Mehrabi, Rahul Gupta, Zhou Yu, Ruoxi Jia

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

详情

展开后加载摘要…

URL PDF HTML 收藏