AI Agent - arXivDaily 专题

2509.00280 2025-09-03 cs.LG cs.DC cs.PF 70%

ReLATE: Learning Efficient Sparse Encoding for High-Performance Tensor Decomposition

Ahmed E. Helal, Fabio Checconi, Jan Laukemann, Yongseok Soh, Jesmin Jahan Tithi, Fabrizio Petrini, Jee Choi

机构 * Intel Corporation（英特尔公司）； University of Erlangen-Nürnberg（埃尔兰根-纽伦堡大学）； University of Oregon（俄勒冈大学）

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

2507.13334 2025-07-22 cs.CL 70%

A Survey of Context Engineering for Large Language Models

Lingrui Mei, Jiayu Yao, Yuyao Ge, Yiwei Wang, Baolong Bi, Yujun Cai, Jiazhi Liu, Mingyu Li, Zhong-Zhi Li, Duzhen Zhang, Chenlin Zhou, Jiayi Mao, Tianze Xia, Jiafeng Guo, Shenghua Liu

机构 * Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）； University of California, Merced（加州大学默塞德分校）； The University of Queensland（昆士兰大学）； Peking University（北京大学）； Tsinghua University（清华大学）； University of Chinese Academy of Sciences（中国科学院大学）

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

Comments ongoing work; 166 pages, 1411 citations

2507.03993 2025-07-08 cs.CR cs.ET cs.LG 70%

MalVol-25: A Diverse, Labelled and Detailed Volatile Memory Dataset for Malware Detection and Response Testing and Validation

Dipo Dunsin, Mohamed Chahine Ghanem, Eduardo Almeida Palmieri

机构 * London Metropolitan University（伦敦 Metropolitan 大学）； Cyber Security Research Centre（网络安全研究中心）； Cybersecurity Institute（网络安全研究所）； Department of Computer Science（计算机科学系）

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

Comments 6 pages

2505.06518 2025-07-08 cs.AI 70%

Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective

Larry Preuett, Qiuyi Zhang, Muhammad Aurangzeb Ahmad

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

Comments Accepted to the Finding the Frame Workshop at the Reinforcement Learning Conference (RLC) 2025. Code available at: https://github.com/lpreuettUW/distributional_point_based_value_iteration

2501.10316 2025-07-01 cs.CL 70%

Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling

Suvodip Dey, Yi-Jyun Sun, Gokhan Tur, Dilek Hakkani-Tur

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

Comments Accepted at ACL 2025 Main Conference

2502.15727 2025-07-01 cs.NI cs.AI cs.CR cs.IR 70%

Retrieval Augmented Generation Based LLM Evaluation For Protocol State Machine Inference With Chain-of-Thought Reasoning

Youssef Maklad, Fares Wael, Wael Elsersy, Ali Hamdi

机构 * Faculty of Computer Science, MSA University（计算机科学学院，MSA大学）

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

Comments Minor modifications in sections: abstract, introduction, background problem formulation, and conclusion. (Typos and Clarifications)

2506.05810 2025-06-09 cs.AI cs.RO 70%

Trajectory Entropy: Modeling Game State Stability from Multimodality Trajectory Prediction

Yesheng Zhang, Wenjian Sun, Yuheng Chen, Qingwei Liu, Qi Lin, Rui Zhang, Xu Zhao

机构 * Department of Automation, Shanghai Jiao Tong University（上海交通大学自动化系）； SAIC-ZONE Technology Co. Ltd.（SAIC-ZONE技术有限公司）

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

Comments 10 pages

2506.04180 2025-06-05 cs.CL 70%

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

Yuhao Wu, Yushi Bai, Zhiqiang Hu, Juanzi Li, Roy Ka-Wei Lee

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

2505.24155 2025-06-02 cs.LG 70%

Biological Pathway Guided Gene Selection Through Collaborative Reinforcement Learning

Ehtesamul Azim, Dongjie Wang, Tae Hyun Hwang, Yanjie Fu, Wei Zhang

机构 * University of Central Florida（佛罗里达中央大学）； University of Kansas（堪萨斯大学）； Vanderbilt University Medical Center（范德比尔特大学医学中心）； Arizona State University（亚利桑那州立大学）

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

Comments 31st SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2025)

2505.22006 2025-05-29 cs.AI cs.CV 70%

Efficiently Enhancing General Agents With Hierarchical-categorical Memory

Changze Qiao, Mingming Lu

专题命中记忆与上下文管理：agent(abstract)；tool-use(abstract)；分类 cs.AI

2503.23631 2025-05-29 cs.AI 70%

Intrinsically-Motivated Humans and Agents in Open-World Exploration

Aly Lidayan, Yuqing Du, Eliza Kosoy, Maria Rufova, Pieter Abbeel, Alison Gopnik

机构 * BAIR ； University of California Berkeley（加州大学伯克利分校）； Psychology（心理学）

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

2405.15907 2025-04-16 cs.AI 70%

Belief-State Query Policies for User-Aligned POMDPs

Daniel Bramblett, Siddharth Srivastava

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

2503.15079 2025-03-20 cs.SE 70%

LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-Agents

Ke Zhang, Chenxi Zhang, Chong Wang, Chi Zhang, YaChen Wu, Zhenchang Xing, Yang Liu, Qingshan Li, Xin Peng

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

2408.07982 2025-02-19 cs.HC cs.AI cs.RO 70%

Toward a Dialogue System Using a Large Language Model to Recognize User Emotions with a Camera

Hiroki Tanioka, Tetsushi Ueta, Masahiko Sano

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

Comments 4 pages, 5 figures, 1 table, The 1st InterAI: Interactive AI for Human-Centered Robotics workshop in conjunction with IEEE Ro-MAN 2024, Pasadona, LA, USA, Aug. 2024

Journal ref The 1st InterAI Workshop: Interactive AI for Human-centered Robotics, 2024

2501.14734 2025-01-28 cs.DC cs.AI 70%

Research on the Application of Spark Streaming Real-Time Data Analysis System and large language model Intelligent Agents

Jialin Wang, Zhihua Duan

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

2411.12313 2024-11-20 cs.LG cs.CV 70%

C$^{2}$INet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Intervention

Xiaohe Li, Feilong Huang, Zide Fan, Fangli Mou, Leilei Lin, Yingyan Hou, Lijie Wen

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

2411.07690 2024-11-13 cs.AI 70%

World Models: The Safety Perspective

Zifan Zeng, Chongzhe Zhang, Feng Liu, Joseph Sifakis, Qunli Zhang, Shiming Liu, Peng Wang

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

Comments 8 pages, 3 figures, accepted at the International Workshop on Dependability Modeling and Design (WDMD) during the IEEE International Symposium on Software Reliability Engineering (ISSRE)

2401.17835 2024-11-04 cs.LG 70%

Simplifying Latent Dynamics with Softly State-Invariant World Models

Tankred Saanum, Peter Dayan, Eric Schulz

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

2407.12784 2024-07-18 cs.LG cs.CR cs.IR 70%

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Zhaorun Chen, Zhen Xiang, Chaowei Xiao, Dawn Song, Bo Li

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

Comments 22 pages, 13 figures, 7 tables

2307.05793 2024-07-09 cs.AI cs.RO 70%

Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building

Jaedong Hwang, Zhang-Wei Hong, Eric Chen, Akhilan Boopathy, Pulkit Agrawal, Ila Fiete

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

Comments TMLR (Featured Certification)

2307.00907 2024-03-07 cs.LG cs.CR cs.MA 70%

Enhancing the Robustness of QMIX against State-adversarial Attacks

Weiran Guo, Guanjun Liu, Ziyuan Zhou, Ling Wang, Jiacun Wang

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

2311.05997 2023-12-01 cs.AI 70%

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

Zihao Wang, Shaofei Cai, Anji Liu, Yonggang Jin, Jinbing Hou, Bowei Zhang, Haowei Lin, Zhaofeng He, Zilong Zheng, Yaodong Yang, Xiaojian Ma, Yitao Liang

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

Comments update project page

2306.01243 2023-10-30 cs.LG 70%

Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations

Minshuo Chen, Jie Meng, Yu Bai, Yinyu Ye, H. Vincent Poor, Mengdi Wang

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

2308.00199 2023-08-02 cs.RO cs.CV cs.LG 70%

CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics

Ali Ayub, Alan R. Wagner

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

Comments Accepted to IEEE Transactions on Cognitive and Developmental Systems

2307.05067 2023-07-12 cs.LO cs.AI 70%

Exploiting Asymmetry in Logic Puzzles: Using ZDDs for Symbolic Model Checking Dynamic Epistemic Logic

Daniel Miedema, Malvin Gattinger

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

Comments In Proceedings TARK 2023, arXiv:2307.04005

Journal ref EPTCS 379, 2023, pp. 407-420

2305.19937 2023-06-01 cs.CV cs.AI 70%

Breast Cancer Detection and Diagnosis: A comparative study of state-of-the-arts deep learning architectures

Brennon Maistry, Absalom E. Ezugwu

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

2301.12055 2023-01-31 cs.LG 70%

TIDo: Source-free Task Incremental Learning in Non-stationary Environments

Abhinit Kumar Ambastha, Leong Tze Yun

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

2109.13392 2023-01-24 cs.AI 70%

The Tensor Brain: A Unified Theory of Perception, Memory and Semantic Decoding

Volker Tresp, Sahand Sharifzadeh, Hang Li, Dario Konopatzki, Yunpu Ma

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

Comments Neural Computation, Volume 35, Issue 2, February 2023

Journal ref Neural Computation, Volume 35, Issue 2, February 2023

2211.15792 2023-01-09 cs.LG cs.GT cs.MA cs.SY eess.SY 70%

Provably Efficient Model-free RL in Leader-Follower MDP with Linear Function Approximation

Arnob Ghosh

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

Comments arXiv admin note: text overlap with arXiv:2206.11889

2212.01861 2022-12-06 cs.LG cs.LO 70%

Online Shielding for Reinforcement Learning

Bettina Könighofer, Julian Rudolf, Alexander Palmisano, Martin Tappler, Roderick Bloem

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

Comments arXiv admin note: substantial text overlap with arXiv:2012.09539

1. 记忆与上下文管理 4766 篇

ReLATE: Learning Efficient Sparse Encoding for High-Performance Tensor Decomposition

A Survey of Context Engineering for Large Language Models

MalVol-25: A Diverse, Labelled and Detailed Volatile Memory Dataset for Malware Detection and Response Testing and Validation

Reinforcement Learning under State and Outcome Uncertainty: A Foundational Distributional Perspective

Know Your Mistakes: Towards Preventing Overreliance on Task-Oriented Conversational AI Through Accountability Modeling

Retrieval Augmented Generation Based LLM Evaluation For Protocol State Machine Inference With Chain-of-Thought Reasoning

Trajectory Entropy: Modeling Game State Stability from Multimodality Trajectory Prediction

SuperWriter: Reflection-Driven Long-Form Generation with Large Language Models

Biological Pathway Guided Gene Selection Through Collaborative Reinforcement Learning

Efficiently Enhancing General Agents With Hierarchical-categorical Memory

Intrinsically-Motivated Humans and Agents in Open-World Exploration

Belief-State Query Policies for User-Aligned POMDPs

LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-Agents

Toward a Dialogue System Using a Large Language Model to Recognize User Emotions with a Camera

Research on the Application of Spark Streaming Real-Time Data Analysis System and large language model Intelligent Agents

C$^{2}$INet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Intervention

World Models: The Safety Perspective

Simplifying Latent Dynamics with Softly State-Invariant World Models

AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases

Grid Cell-Inspired Fragmentation and Recall for Efficient Map Building

Enhancing the Robustness of QMIX against State-adversarial Attacks

JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models

Efficient Reinforcement Learning with Impaired Observability: Learning to Act with Delayed and Missing State Observations

CBCL-PR: A Cognitively Inspired Model for Class-Incremental Learning in Robotics

Exploiting Asymmetry in Logic Puzzles: Using ZDDs for Symbolic Model Checking Dynamic Epistemic Logic

Breast Cancer Detection and Diagnosis: A comparative study of state-of-the-arts deep learning architectures

TIDo: Source-free Task Incremental Learning in Non-stationary Environments

The Tensor Brain: A Unified Theory of Perception, Memory and Semantic Decoding

Provably Efficient Model-free RL in Leader-Follower MDP with Linear Function Approximation

Online Shielding for Reinforcement Learning