AI Agent - arXivDaily 专题

1610.01546 2016-10-06 cs.CL cs.IR cs.LG 62%

Conversational Recommendation System with Unsupervised Learning

Yueming Sun, Yi Zhang, Yunfei Chen, Roger Jin

专题命中 Agent评测：agent(abstract)；分类 cs.CL、cs.LG

1609.01468 2016-09-07 cs.LG cs.AI stat.ML 62%

Q-Learning with Basic Emotions

Wilfredo Badoy, Kardi Teknomo

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 7 pages, Badoy, W. and Teknomo, K. (2014) Q-Learning with Basic Emotions, Proceeding of the 7th IEEE International Conference Humanoid, Nanotechnology, Information Technology Communication and Control, Environment and Management (HNICEM) 12-16 November 2014 Hotel Centro, Puerto Princesa, Palawan, Philippines

cs/0505058 2016-08-31 cs.CV astro-ph cs.AI cs.CE cs.HC cs.RO cs.SE physics.ins-det q-bio.NC 62%

The Cyborg Astrobiologist: Scouting Red Beds for Uncommon Features with Geological Significance

Patrick C. McGuire, Enrique Diaz-Martinez, Jens Ormo, Javier Gomez-Elvira, Jose A. Rodriguez-Manfredi, Eduardo Sebastian-Martinez, Helge Ritter, Robert Haschke, Markus Oesker, Joerg Ontrup

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.SE

Comments to appear in Int'l J. Astrobiology, vol.4, iss.2 (June 2005); 19 pages, 7 figs

Journal ref Int.J.Astrobiol.4:101-113,2005

1608.01127 2016-08-04 cs.RO cs.AI cs.CV cs.LG 62%

Autonomous Grounding of Visual Field Experience through Sensorimotor Prediction

Alban Laflaquière

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 6 pages, 4 figures, ICDL-Epirob 2016

1608.00359 2016-08-02 cs.RO cs.AI cs.LG 62%

Discovering Latent States for Model Learning: Applying Sensorimotor Contingencies Theory and Predictive Processing to Model Context

Nikolas J. Hemion

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

1606.07056 2016-06-23 cs.AI cs.CL cs.IR 62%

Emulating Human Conversations using Convolutional Neural Network-based IR

Abhay Prakash, Chris Brockett, Puneet Agrawal

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.CL

Comments 5 pages, Neu-IR'16 SIGIR Workshop on Neural Information Retrieval, July 21, 2016, Pisa, Italy

1604.03692 2016-04-22 cs.RO cs.AI cs.CV cs.LG 62%

Learning Social Affordance for Human-Robot Interaction

Tianmin Shu, M. S. Ryoo, Song-Chun Zhu

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments International Joint Conference on Artificial Intelligence (IJCAI), 2016

1603.04119 2016-03-15 cs.AI cs.LG stat.ML 62%

Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains

David Abel, Alekh Agarwal, Fernando Diaz, Akshay Krishnamurthy, Robert E. Schapire

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

1512.07650 2015-12-25 stat.ML cs.AI cs.LG 62%

The Max $K$-Armed Bandit: PAC Lower Bounds and Efficient Algorithms

Yahel David, Nahum Shimkin

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments arXiv admin note: substantial text overlap with arXiv:1508.05608

1507.04124 2015-10-20 cs.AI cs.LG 62%

On the Computability of Solomonoff Induction and Knowledge-Seeking

Jan Leike, Marcus Hutter

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments ALT 2015

1508.05608 2015-08-25 stat.ML cs.AI cs.LG 62%

The Max $K$-Armed Bandit: A PAC Lower Bound and tighter Algorithms

Yahel David, Nahum Shimkin

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

1507.08482 2015-07-31 quant-ph cs.AI cs.LG 62%

Framework for learning agents in quantum environments

Vedran Dunjko, Jacob M. Taylor, Hans J. Briegel

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 39 pages, 7 figures

1502.05774 2015-06-09 cs.GT cs.AI cs.LG stat.ML 62%

Low-Cost Learning via Active Data Procurement

Jacob Abernethy, Yiling Chen, Chien-Ju Ho, Bo Waggoner

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments Full version of EC 2015 paper. Color recommended for figures but nonessential. 36 pages, of which 12 appendix

1306.2268 2013-06-11 cs.AI cs.CL 62%

Accomplishable Tasks in Knowledge Representation

Keehang Kwon, Mi-Young Park

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.CL

Comments arXiv admin note: substantial text overlap with arXiv:1305.2004

1107.5537 2012-02-10 cs.AI cs.LG 62%

Asymptotically Optimal Agents

Tor Lattimore, Marcus Hutter

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 21 LaTeX pages

Journal ref Proc. 22nd International Conf. on Algorithmic Learning Theory (ALT-2011) pages 368-382

1201.6604 2012-02-01 cs.AI cs.LG 62%

Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-like Exploration

Tobias Jung, Peter Stone

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments European Conference on Machine Learning (ECML'2010)

0810.3605 2010-04-13 cs.AI cs.LG 62%

A Minimum Relative Entropy Principle for Learning and Acting

Pedro A. Ortega, Daniel A. Braun

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 36 pages, 11 figures

0911.5104 2010-01-07 cs.AI cs.LG 62%

A Bayesian Rule for Adaptive Control based on Causal Interventions

Pedro A. Ortega, Daniel A. Braun

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments AGI-2010. 6 pages, 2 figures

Journal ref AGI-2010

0812.5032 2009-12-01 cs.LG cs.AI cs.CV physics.soc-ph 62%

A New Clustering Algorithm Based Upon Flocking On Complex Network

Qiang Li, Yan He, Jing-ping Jiang

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 18 pages, 4 figures, 3 tables

cs/0701125 2009-12-01 cs.AI cs.LG 62%

Universal Algorithmic Intelligence: A mathematical top->down approach

Marcus Hutter

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 70 pages

Journal ref In Artificial General Intelligence, Springer (2007) 227-290

cs/0603110 2009-12-01 cs.LG cs.AI 62%

Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence

Daniil Ryabko, Marcus Hutter

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 15 pages

Journal ref Proc. 17th International Conf. on Algorithmic Learning Theory (ALT 2006) pages 334-347

cs/0602018 2009-12-01 cs.CY cs.AI cs.CL cs.HC cs.MA 62%

Improving the CSIEC Project and Adapting It to the English Teaching and Learning in China

Jiyou Jia, Shufen Hou, Weichao Chen

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.CL

cs/0012011 2009-11-30 cs.AI cs.CC cs.IT cs.LG math.IT 62%

Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory

Marcus Hutter

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 8 two-column pages, latex2e, 1 figure, submitted to ijcai

Journal ref Lecture Notes in Artificial Intelligence (LNAI 2167), Proc. 12th Eurpean Conf. on Machine Learning, ECML (2001) 226--238

cs/0004001 2009-11-30 cs.AI cs.IT cs.LG math.IT 62%

A Theory of Universal Artificial Intelligence based on Algorithmic Complexity

Marcus Hutter

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 62 pages, LaTeX

cs/0105025 2009-11-30 cs.AI cs.LG cs.MA cs.NE 62%

Market-Based Reinforcement Learning in Partially Observable Worlds

Ivo Kwee, Marcus Hutter, Juergen Schmidhuber

专题命中 Agent评测：agent(abstract)；分类 cs.AI、cs.LG

Comments 8 LaTeX pages, 2 postscript figures

Journal ref Lecture Notes in Computer Science (LNCS 2130), Proceeding of the International Conference on Artificial Neural Networks ICANN (2001) 865-873

2605.23262 2026-08-25 cs.AI 版本更新 61%

Designing Benchmarks for Knowledge Work

知识工作的设计与报告基准

Yining Hua, Hongbin Na, Cyrus Ayubcha, Levi Lian

机构 * Harvard University（哈佛大学）； University of Technology Sydney（悉尼科技大学）； Stanford University（斯坦福大学）； Raycaster AI

专题命中 Agent评测：AI agent(abstract)；分类 cs.AI；agent(comments)

AI总结针对当前知识工作评估基准与真实部署脱节的问题，提出三步法（定义工作活动、指定测试设置、评分工作产品）来明确基准任务与工作主张的对应关系，并通过三个案例分析展示设计选择如何影响可支持的工作主张。

Comments 18 pages. This replacement updates the title and revises the contribution from a three-step reporting approach to a four-field work-centered benchmark representation (represented activity, tested setting, required work product, and evaluated result). Author affiliations now include Agent Evaluation Science, Inc., New York, NY 10001

2603.28200 2026-08-24 cs.RO cs.LG q-bio.PE 版本更新 61%

A Deep Reinforcement Learning Framework for Closed-loop Guidance of Fish Schools via Virtual Agents

通过虚拟代理实现鱼群闭环引导的深度强化学习框架

Takato Shibayama, Hiroaki Kawashima

专题命中 Agent评测：agent(abstract,comments)；分类 cs.LG

AI总结本文提出基于深度强化学习的鱼群闭环引导框架，利用虚拟代理进行实时交互，通过复合奖励函数平衡方向引导与社会凝聚力，并发现物理实验中白底和较大刺激尺寸能提升引导效果，但群体规模增大时引导能力显著下降。

Comments 29 pages, 10 figures. Revised version with additional statistical and agent-behavior analyses. Corrections and improvements throughout

2106.06060 2026-08-24 cs.MA cs.AI cs.GT 版本更新 61%

AI-driven Prices for Externalities and Sustainability in Production Markets

生产市场中外部性与可持续性的AI驱动定价

Panayiotis Danassis, Aris Filos-Ratsikas, Haipeng Chen, Milind Tambe, Boi Faltings

专题命中 Agent评测：agent(abstract)；分类 cs.AI；autonomous agent(comments)

AI总结该研究针对传统竞争市场未考虑负外部性的问题，提出深度强化学习策略智能体方法调整生产市场价格，在稀缺资源环境中维持资源可持续性的效果优于市场均衡结果。

Comments Accepted to the 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023)

2608.18104 2026-08-20 cs.AI 新提交 61%

Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective

自进化智能体作为动态图变换：一项综述与新视角

Yuanyuan Xu, Wenjie Zhang, Yin Chen, Xuemin Lin, Ying Zhang

机构 * School of Computer Science and Engineering, The University of New South Wales（新南威尔士大学计算机科学与工程学院）； Faculty of Engineering and Information Technology, University of Technology Sydney（悉尼科技大学工程与信息技术学院）； School of Data Science, The Chinese University of Hong Kong-Shenzhen（香港中文大学（深圳）数据科学学院）； Zhejiang Gongshang University（浙江工商大学）

专题命中 Agent评测：agent(abstract,comments)；分类 cs.AI

AI总结本综述将自进化智能体建模为动态图变换，梳理相关动态图方法分类，提出动态图学习作为智能体可复用基础设施，探讨图感知评估协议，为自进化智能体设计治理提供结构性视角。

Comments Project: https://github.com/LuckyGirl-XU/Awesome-Agent-Dynamic-Graphs.git

2608.16813 2026-08-18 cs.AI cs.DB 新提交 61%

Quipu: A Governed Bitemporal Knowledge Graph Store

Quipu：一种受管控的双时态知识图存储系统

Steve Brown

专题命中 Agent评测：agent(abstract,comments)；分类 cs.AI

AI总结研究针对智能体知识图存储的四项默认规则缺陷，提出受管控双时态知识图存储系统Quipu，经Census、DEMM-Bench等基准测试，其在缺陷检测、裁决准确性、管控问题回答等方面表现优于基线。

Comments 15 pages, 2 figures, 4 tables. Subtitle: "Start strict: rethinking knowledge-graph defaults for agent-written knowledge". Source and the benchmark/census/ artifacts behind every reported number are archived at doi:10.5281/zenodo.21878428 (concept DOI, resolves to newest release). Development repository: github.com/scbrown/quipu

1. Agent评测 15819 篇

Conversational Recommendation System with Unsupervised Learning

Q-Learning with Basic Emotions

The Cyborg Astrobiologist: Scouting Red Beds for Uncommon Features with Geological Significance

Autonomous Grounding of Visual Field Experience through Sensorimotor Prediction

Discovering Latent States for Model Learning: Applying Sensorimotor Contingencies Theory and Predictive Processing to Model Context

Emulating Human Conversations using Convolutional Neural Network-based IR

Learning Social Affordance for Human-Robot Interaction

Exploratory Gradient Boosting for Reinforcement Learning in Complex Domains

The Max $K$-Armed Bandit: PAC Lower Bounds and Efficient Algorithms

On the Computability of Solomonoff Induction and Knowledge-Seeking

The Max $K$-Armed Bandit: A PAC Lower Bound and tighter Algorithms

Framework for learning agents in quantum environments

Low-Cost Learning via Active Data Procurement

Accomplishable Tasks in Knowledge Representation

Asymptotically Optimal Agents

Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-like Exploration

A Minimum Relative Entropy Principle for Learning and Acting

A Bayesian Rule for Adaptive Control based on Causal Interventions

A New Clustering Algorithm Based Upon Flocking On Complex Network

Universal Algorithmic Intelligence: A mathematical top->down approach

Asymptotic Learnability of Reinforcement Problems with Arbitrary Dependence

Improving the CSIEC Project and Adapting It to the English Teaching and Learning in China

Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory

A Theory of Universal Artificial Intelligence based on Algorithmic Complexity

Market-Based Reinforcement Learning in Partially Observable Worlds

Designing Benchmarks for Knowledge Work

A Deep Reinforcement Learning Framework for Closed-loop Guidance of Fish Schools via Virtual Agents

AI-driven Prices for Externalities and Sustainability in Production Markets

Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New Perspective

Quipu: A Governed Bitemporal Knowledge Graph Store