AI Agent - arXivDaily 专题

2110.12579 2021-10-26 cs.MA cs.HC cs.PL 67%

Observable and Attention-Directing BDI Agents for Human-Autonomy Teaming

Blair Archibald, Muffy Calder, Michele Sevegnani, Mengwei Xu

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

Comments In Proceedings FMAS 2021, arXiv:2110.11527

Journal ref EPTCS 348, 2021, pp. 167-175

2011.01057 2021-08-09 cs.MA cs.DC 67%

The Persistence of False Memory: Brain in a Vat Despite Perfect Clocks

Thomas Schlögl, Ulrich Schmid, Roman Kuznets

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

Comments 34 pages, 2 figures

Journal ref Proceedings of PRIMA 2020, LNCS v. 12568 (2021), pp. 403-411

2103.11325 2021-07-16 eess.SY cs.SY 67%

A Proximal Point Approach for Distributed System State Estimation

Marco Fabris, Giulia Michieletto, Angelo Cenedese

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

Comments 6 pages, 2 figures, 1 table, manuscript n 3555, \c{opyright} 2020 the authors. This work has been accepted to IFAC for publication under a Creative Commons Licence CC-BY-NC-ND

Journal ref IFAC-PapersOnLine, Volume 53, Issue 2, 2020, Pages 2702-2707

2107.00691 2021-07-07 cs.CV 67%

Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization

S. Ehsan Mirsadeghi, Ali Royat, Hamid Rezatofighi

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

Journal ref IEEE Robotics and Automation Letters (RA-L 2021) & IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)

2106.15964 2021-07-01 eess.SP 67%

AI-Based Secure NOMA and Cognitive Radio enabled Green Communications: Channel State Information and Battery Value Uncertainties

Saeed Sheikhzadeh, Mohsen Pourghasemian, Mohammad R. Javan, Nader Mokari, Eduard A. Jorswieck

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

2011.09871 2021-04-28 math.OC 67%

Learning-based State Reconstruction for a Scalar Hyperbolic PDE under noisy Lagrangian Sensing

M. Barreau, J. Liu, K. H. Johansson

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

Journal ref Proceedings of Machine Learning Research vol 144:1-16, 2021

2104.11902 2021-04-27 cs.LG cs.AI cs.CL 67%

Ask & Explore: Grounded Question Answering for Curiosity-Driven Exploration

Jivat Neet Kaur, Yiding Jiang, Paul Pu Liang

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

Comments Accepted at ICLR 2021 Workshop on Embodied Multimodal Learning

2012.09539 2020-12-18 cs.LO 67%

Online Shielding for Stochastic Systems

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)

Comments 18 Pages, 6 Figures, under submission

1907.09070 2020-09-15 cs.GT math.OC 67%

Bayesian Persuasion with State-Dependent Quadratic Cost Measures

Muhammed O. Sayin, Tamer Basar

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

2006.01016 2020-06-02 cs.AI cs.CL cs.LG 67%

Probing Emergent Semantics in Predictive Agents via Question Answering

Abhishek Das, Federico Carnevale, Hamza Merzic, Laura Rimell, Rosalia Schneider, Josh Abramson, Alden Hung, Arun Ahuja, Stephen Clark, Gregory Wayne, Felix Hill

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

Comments ICML 2020

2005.03169 2020-05-12 eess.SY cs.SY 67%

On Optimal Control of Discounted Cost Infinite-Horizon Markov Decision Processes Under Local State Information Structures

Guanze Peng, Veeraruna Kavitha, Qunayan Zhu

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

2002.08795 2020-02-21 cs.LG cs.AI cs.CL 67%

How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents

Prithviraj Ammanabrolu, Ethan Tien, Zhaochen Luo, Mark O. Riedl

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

2001.08837 2020-01-27 cs.LG cs.AI cs.CL stat.ML 67%

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

Prithviraj Ammanabrolu, Matthew Hausknecht

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

Comments Accepted to ICLR 2020

2001.05755 2020-01-17 cs.CV 67%

ScaIL: Classifier Weights Scaling for Class Incremental Learning

Eden Belouadah, Adrian Popescu

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

Comments 8 pages, 4 figures, 2 tables, accepted in WACV2020

1902.09368 2019-08-30 cs.CV 67%

Dual Attention Networks for Visual Reference Resolution in Visual Dialog

Gi-Cheon Kang, Jaeseo Lim, Byoung-Tak Zhang

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

Comments EMNLP 2019

1811.10681 2019-08-20 cs.CV 67%

Matching Features without Descriptors: Implicitly Matched Interest Points

Titus Cieslewski, Michael Bloesch, Davide Scaramuzza

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

Comments 10 pages without references, accepted for publication at the British Machine Vision Conference (BMVC), Cardiff, 2019. v2 contains additional results, and a bug in the evaluation of LF-NET has been fixed

Journal ref British Machine Vision Conference (BMVC), Cardiff, 2019

1907.06768 2019-07-18 cs.DC 67%

Partitioning Graphs for the Cloud using Reinforcement Learning

Mohammad Hasanzadeh Mofrad, Rami Melhem, Mohammad Hammoud

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

1906.09310 2019-06-25 cs.LG cs.AI cs.CL 67%

A Study of State Aliasing in Structured Prediction with RNNs

Layla El Asri, Adam Trischler

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

Comments Deep Reinforcement Learning Meets Structured Prediction workshop at ICLR 2019 and Representation Learning for NLP workshop at ACL 2019

1811.05013 2018-11-14 cs.CV cs.AI cs.CL cs.LG 67%

Blindfold Baselines for Embodied QA

Ankesh Anand, Eugene Belilovsky, Kyle Kastner, Hugo Larochelle, Aaron Courville

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

Comments NIPS 2018 Visually-Grounded Interaction and Language (ViGilL) Workshop

1712.03316 2018-09-07 cs.CV 67%

IQA: Visual Question Answering in Interactive Environments

Daniel Gordon, Aniruddha Kembhavi, Mohammad Rastegari, Joseph Redmon, Dieter Fox, Ali Farhadi

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

Comments Published in CVPR 2018

1609.06678 2016-09-22 cs.NI 67%

Consistency Maintenance of State of Management Data in P2P-based Autonomic Network Management

Jéferson Campos Nobre, Lisandro Zambenedetti Granville

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

Comments 25 pages

1607.00397 2016-07-27 math.DS physics.soc-ph 67%

Interaction Network, State Space and Control in Social Dynamics

Aylin Aydogdu, Marco Caponigro, Sean McQuade, Benedetto Piccoli, Nastassia Pouradier Duteil, Francesco Rossi, Emmanuel Trélat

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

Comments Chapter of the Birkhauser-Springer book (to appear) by N. Bellomo, P. Degond, and E. Tadmor Eds., "Active Particles Volume 1, Theory, Methods, and Applications"

1605.07960 2016-05-26 cs.CV cs.RO 67%

Multi-Object Tracking and Identification over Sets

Aijun Bai

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

Comments Draft version

1506.04089 2015-12-18 cs.CL cs.AI cs.LG cs.NE cs.RO 67%

Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences

Hongyuan Mei, Mohit Bansal, Matthew R. Walter

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

Comments To appear at AAAI 2016 (and an extended version of a NIPS 2015 Multimodal Machine Learning workshop paper)

cond-mat/0312556 2009-12-01 cond-mat.stat-mech q-bio.QM 67%

Memory and self-induced shocks in an evolutionary population competing for limited resources

Roland Kay, Neil F. Johnson

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

Comments 27 pages, 31 figures

physics/0607001 2009-12-01 physics.data-an physics.soc-ph 67%

Naming Game on small-world networks: the role of clustering structure

Bo-Yu Lin, Jie Ren, Hui-Jie Yang, Bing-Hong Wang

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

Comments 6 pages, 8 figures, Research Program for Undergraduate in USTC

2207.09845 2026-04-29 cs.RO cs.AI cs.HC cs.LG 66%

Quantifying the Effect of Feedback Frequency in Interactive Reinforcement Learning for Robotic Tasks

量化交互强化学习在机器人任务中的反馈频率效应

Daniel Harnack, Julie Pivin-Bachler, Nicolás Navarro-Guerrero

机构 * Robotics and Interactive Systems – UPSSITECH, University Paul Sabatier（机器人与交互系统——UPSSITECH，保罗·萨巴蒂埃大学）

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

AI总结研究探讨了反馈频率对机器人任务中交互强化学习效率的影响，通过不同复杂度的机械臂逆运动学学习实验，发现反馈频率需随任务熟练度动态调整，无单一最优频率。

Comments Neural Computing and Applications (2022). Special Issue on Human-aligned Reinforcement Learning for Autonomous Agents and Robots

2603.15658 2026-03-18 cs.AI cs.CL cs.IR 66%

Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents

你检查了正确的口袋吗？面向内存增强代理的成本敏感存储路由

Madhava Gaikwad

机构 * ICLR 2026 Workshop on Memory and State in LLM-Based Agents（ICLR 2026 记忆与状态在大语言模型代理中的工作坊）

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

AI总结本文提出通过成本敏感存储路由优化内存增强代理的检索效率，通过覆盖、精确匹配和令牌效率指标评估，证明选择性检索能提升效率和性能，推动了可扩展多存储系统的 learned routing 机制发展。

Comments accepted in ICLR 2026 Workshop on Memory for LLM-Based Agentic Systems

2512.07853 2025-12-10 cs.LG cs.AI cs.DC 66%

GPU Memory Prediction for Multimodal Model Training

多模态模型训练的GPU内存预测

Jinwoo Jeong, Minchul Kang, Younghun Go, Changyong Shin, Hyunho Lee, Junho Yoon, Gyeongsik Yang, Chuck Yoo

机构 * Korea University（韩国大学）； KT Corporation（KT公司）

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

AI总结本文提出了一种用于多模态模型训练的GPU内存预测框架，通过分解模型结构和分析训练行为，实现了高精度的内存预测。

Comments 1st Workshop on Systems for Agentic AI (SAA '25), co-located with SOSP 2025

2301.05630 2023-01-16 cs.LG cs.AI cs.GT cs.MA 66%

Decentralized model-free reinforcement learning in stochastic games with average-reward objective

Romain Cravic, Nicolas Gast, Bruno Gaujal

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

Comments Accepted to the 22th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023). This version is the full version with proofs in appendix

1. 记忆与上下文管理 4786 篇

Observable and Attention-Directing BDI Agents for Human-Autonomy Teaming

The Persistence of False Memory: Brain in a Vat Despite Perfect Clocks

A Proximal Point Approach for Distributed System State Estimation

Unsupervised Image Segmentation by Mutual Information Maximization and Adversarial Regularization

AI-Based Secure NOMA and Cognitive Radio enabled Green Communications: Channel State Information and Battery Value Uncertainties

Learning-based State Reconstruction for a Scalar Hyperbolic PDE under noisy Lagrangian Sensing

Ask & Explore: Grounded Question Answering for Curiosity-Driven Exploration

Online Shielding for Stochastic Systems

Bayesian Persuasion with State-Dependent Quadratic Cost Measures

Probing Emergent Semantics in Predictive Agents via Question Answering

On Optimal Control of Discounted Cost Infinite-Horizon Markov Decision Processes Under Local State Information Structures

How To Avoid Being Eaten By a Grue: Exploration Strategies for Text-Adventure Agents

Graph Constrained Reinforcement Learning for Natural Language Action Spaces

ScaIL: Classifier Weights Scaling for Class Incremental Learning

Dual Attention Networks for Visual Reference Resolution in Visual Dialog

Matching Features without Descriptors: Implicitly Matched Interest Points

Partitioning Graphs for the Cloud using Reinforcement Learning

A Study of State Aliasing in Structured Prediction with RNNs

Blindfold Baselines for Embodied QA

IQA: Visual Question Answering in Interactive Environments

Consistency Maintenance of State of Management Data in P2P-based Autonomic Network Management

Interaction Network, State Space and Control in Social Dynamics

Multi-Object Tracking and Identification over Sets

Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences

Memory and self-induced shocks in an evolutionary population competing for limited resources

Naming Game on small-world networks: the role of clustering structure

Quantifying the Effect of Feedback Frequency in Interactive Reinforcement Learning for Robotic Tasks

Did You Check the Right Pocket? Cost-Sensitive Store Routing for Memory-Augmented Agents

GPU Memory Prediction for Multimodal Model Training

Decentralized model-free reinforcement learning in stochastic games with average-reward objective