AI Agent - arXivDaily 专题

1011.1531 2010-11-13 cs.CR cs.NI 71%

An Agent-Based Intrusion Detection System for Local Area Networks

Jaydip Sen

专题命中 Agent评测：agent(title)

Comments 13 pages, 5 figures, 2 tables

Journal ref International Journal of Communication Networks and Information Security (IJCNIS), Vol 2, No 2, August 2010

physics/0608293 2010-04-27 physics.soc-ph cs.CE q-fin.PM stat.AP 71%

Automatic Trading Agent. RMT based Portfolio Theory and Portfolio Selection

Malgorzata Snarska, Jakub Krzych

专题命中 Agent评测：agent(title)

Comments 13 pages, 7 figures. Presented at the 2nd Polish Seminar on Econo- and Sociophysics, 2006/04/21-22 Cracow. To be published in Acta Phys. Pol. B

Journal ref Acta Phys. Pol. B 37 (2006) 3145

0802.4165 2009-12-01 q-fin.TR nlin.AO 71%

Illusory versus Genuine Control in Agent-Based Games

J. B. Satinover, D. Sornette

专题命中 Agent评测：agent(title)

Comments 22 pages

physics/0509185 2009-12-01 physics.soc-ph cond-mat.dis-nn 71%

Temporal Effects of Agent Aggregation in the Dynamics of Multiagent Systems

C. H. Yeung, K. Y. Michael Wong

专题命中 Agent评测：agent(title)

Comments 7 pages, 5 figures

Journal ref Europhys. Lett. Vol. 75, 357 (2006)

cond-mat/0407626 2009-12-01 cond-mat.other 71%

Heterogeneity and feedback in an agent-based market model

Francois Ghoulmie

专题命中 Agent评测：agent(title)

Comments This paper has been withdrawn

0811.0074 2009-12-01 math.LO 71%

Logical tools for handling change in agent-based systems

Dov Gabbay, Karl Schlechta

专题命中 Agent评测：agent(title)

cond-mat/0404264 2009-12-01 cond-mat.stat-mech cond-mat.dis-nn q-fin.TR 71%

Price return auto-correlation and predictability in agent-based models of financial markets

Damien Challet, Tobias Galla

专题命中 Agent评测：agent(title)

Comments 7 pages, 5 figures

cond-mat/0311257 2009-12-01 cond-mat.stat-mech q-fin.TR 71%

Real payoffs and virtual trading in agent based market models

F. F. Ferreira, M. Marsili

专题命中 Agent评测：agent(title)

Comments 20pages and 15 figures

0712.2687 2009-12-01 q-fin.TR physics.soc-ph 71%

The value of information in financial markets: An agent-based simulation

Bence Toth, Enrico Scalas

专题命中 Agent评测：agent(title)

Comments 25 pages, 7 figures invited paper to "Information, Interaction, and (In)Efficiency in Financial Markets" edited by Juergen Huber and Michael Hanke

0710.0459 2009-12-01 q-fin.GN physics.comp-ph physics.soc-ph 71%

Statistical properties of agent-based market area model

Zoltan Kuscsik, Denis Horvath

专题命中 Agent评测：agent(title)

Comments 5 figures, 7 pages. submited to ICCS 2007, Boston

0805.0428 2009-12-01 nlin.AO 71%

Cycles, determinism and persistence in agent-based games and financial time-series

J. B. Satinover, D. Sornette

专题命中 Agent评测：agent(title)

Comments 58 page including 16 figures and 9 tables

0706.1568 2009-12-01 q-bio.CB 71%

Simulating non-small cell lung cancer with a multiscale agent-based model

Zhihui Wang, Le Zhang, Jonathan Sagotsky, Thomas S. Deisboeck

专题命中 Agent评测：agent(title)

Comments 37 pages, 7 figures

physics/0602003 2009-12-01 physics.soc-ph 71%

Emergent Behavior in Agent Networks: Self-Organization in Wasp and Open Source Communities

Sergi Valverde, Guy Theraulaz, Jacques Gautrais, Vincent Fourcassie, Ricard V. Sole

专题命中 Agent评测：agent(title)

Comments 12 pages, 4 figures. Accepted for publication in the IEEE Intelligent Systems Special Issue on Self-Management through Self-Organization (2006)

cs/0410022 2009-12-01 cs.MM cs.MA 71%

RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA

P. Piwek, B. Krenn, M. Schroeder, M. Grice, S. Baumann, H. Pirker

专题命中 Agent评测：agent(title)

Comments 7 pages, 4 figures

Journal ref In Proceedings of the AAMAS-02 Workshop ``Embodied conversational agents - let's specify and evaluate them!'', July 16 2002, Bologna, Italy.

cond-mat/0407629 2009-12-01 cond-mat.other 71%

Evolution of heterogeneity in an agent-based market model

Francois Ghoulmie

专题命中 Agent评测：agent(title)

Comments This paper has been withdrawn

cond-mat/0406711 2009-12-01 cond-mat.other 71%

Strategic updating of threshold response in an agent-based market model

Francois Ghoulmie

专题命中 Agent评测：agent(title)

Comments This paper has been withdrawn

astro-ph/9805026 2009-12-01 astro-ph 71%

Turbulence as an Organizing Agent in the ISM

Enrique Vazquez-Semadeni, Thierry Passot

专题命中 Agent评测：agent(title)

Comments 9 pages, 4 postscript figures. To appear in "Interstellar Turbulence", eds. P. Franco & A. Carraminana, Cambridge University Press

cond-mat/0206222 2009-11-30 cond-mat 71%

Bubbles, crashes and intermittency in agent based market models

Irene Giardina, Jean-Philippe Bouchaud

专题命中 Agent评测：agent(title)

Comments 44 pages, 12 .ps figures. One figure discussing the Lux-Marchesi model added

cond-mat/0006463 2009-11-30 cond-mat.stat-mech cond-mat.dis-nn q-fin.TR 71%

Diffusion and Aggregation in an Agent Based Model of Stock Market Fluctuations

Filippo Castiglione

专题命中 Agent评测：agent(title)

Comments 17 pages, 8 figures (accepted for publication in Int. J. Mod. Phys. C)

cond-mat/9802177 2009-11-30 cond-mat adap-org nlin.AO 71%

Volatility and Agent Adaptability in a Self-Organizing Market

N. F. Johnson, S. Jarvis, R. Jonson, P. Cheung, Y. R. Kwong, P. M. Hui

专题命中 Agent评测：agent(title)

Comments 8 pages, 3 figs. n.johnson@physics.ox.ac.uk, pmhui@phy.cuhk.edu.hk

math/0211465 2009-11-30 math.GM 71%

Logic: A Misleading Concept. A Contradiction Study toward Agent's Logic

Feng Liu, Florentin Smarandache

专题命中 Agent评测：agent(title)

Comments 10 pages, 6 figure. "Proceedings of the First International Conference on Neutrosophy, Neutrosophic Logic, Neutrosophic Set, Neutrosophic Probability and Statistics", Florentin Smarandache editor, Xiquan, Phoenix, ISBN: 1-931233-55-1, 147 p., 2002

Journal ref "Libertas Mathematica", University of Texas at Arlington, Vol. XXII, pp. 175-187, 2002

cs/0203023 2009-11-30 cs.CE 71%

Agent trade servers in financial exchange systems

David Lyback, Magnus Boman

专题命中 Agent评测：agent(title)

Comments 11 pages, 1 figure

1805.07871 2020-11-19 cs.LG cs.AI stat.ML 71%

A Framework and Method for Online Inverse Reinforcement Learning

Saurabh Arora, Prashant Doshi, Bikramjit Banerjee

专题命中 Agent评测：agent(abstract,journal_ref)；分类 cs.AI、cs.LG；autonomous agent(journal_ref)；multi-agent(journal_ref)

Journal ref Journal of Autonomous Agents and Multi-Agent Systems, Volume 35, Article number: 4 (2021)

2608.19857 2026-08-21 cs.LG cs.CR 新提交 70%

Inadvertent Context Leakage in Language Models

语言模型中的无意上下文泄漏

Jaiden Fairoze, Neal Mangaokar, Kamalika Chaudhuri, Sanjam Garg, Saeed Mahloujifar

机构 * FAIR, Meta Superintelligence Labs（Meta超级智能实验室FAIR）； University of California, Berkeley（加利福尼亚大学伯克利分校）； Google DeepMind（谷歌DeepMind）

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

AI总结该研究发现语言模型的上下文窗口会无意泄漏敏感用户信息，提出自适应攻击方法，在8个专有模型上验证了2、4位数秘密的重建准确率，还展示了两种实际攻击方式，指出泄漏是模型能力的副产品。

2608.19741 2026-08-21 cs.CL cs.DB 新提交 70%

One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows

单次成功并非可靠：Thinkingbox——面向有状态业务工作流智能体的沙箱与基准测试集

Zhuochun Li, Youngmin Ko, Ali Keramati, Nicola Ferri, Susana Palmaz Lopez Pelaez, Liang-Chun Tsai, Calvin Wang, Mirco Milletari, Tuhin Kundu, Vadim Smolyakov, Kjartan Olafsson, Tommy Guy

机构 * University of Pittsburgh（匹兹堡大学）； Northwestern University（西北大学）； University of California Irvine（加州大学欧文分校）； Microsoft（微软公司）

专题命中 Agent评测：agent(abstract)；function calling(abstract)；分类 cs.CL

AI总结研究人员推出面向有状态业务工作流智能体的沙箱Thinkingbox及基准测试集Thinkingbox-bench，发现现有智能体在该基准上可靠完成任务的表现远逊于单次成功表现，凸显了端到端任务可靠评估的必要性。

2608.19511 2026-08-21 cs.AI 新提交 70%

Symposium: Trust via Auditable Records for Communities of AI Scientist Agents

专题讨论会：面向AI科学家智能体社群的可审计记录信任机制

Dexter Pratt

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

AI总结 Symposium是面向AI科学家智能体社群的可审计记录信任框架，通过保留科研活动的不可变历史与科学论证，支持信任评估，且提供可快速部署的实现。

2608.15012 2026-08-18 cs.CR cs.AI cs.MA 新提交 70%

SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system

SysEvolve：一种原生AI、安全且自主的对抗攻防协同进化系统

Yuhan Meng, Shaofei Li, Jionghao Huang, Jiandong Jin, Puyi Wang, Hanlin Jiang, Anis Yusof, Peng Jiang, Zhenkai Liang, Yao Guo, Ding Li

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

AI总结该研究针对网络安全攻防不对称问题，提出SysEvolve协同进化系统，含三个组件，实验验证其攻防性能，还揭示了LLM智能体能力的三项关键发现。

Comments Technical Report For SysEvolve System

2608.12262 2026-08-13 cs.CV cs.AI 新提交 70%

Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams

Diagram-MMU：面向科学图表的多模态基准测试

Weihao Bo, Shan Zhang, Yanpeng Sun, Jie Liu, Yongke Yao, Jinhao Du, Wei He, Kai Zou, Zechao Li, Jingdong Wang

机构 * Nanjing University of Science and Technology（南京理工大学）； Baidu Inc（百度公司）； AIML, Adelaide University（阿德莱德大学AIML）； SUTD（新加坡科技设计大学）； Southeast University（东南大学）； East China Normal University（华东师范大学）； University of Oxford（牛津大学）

专题命中 Agent评测：agentic(abstract,abstract_cn)；分类 cs.AI

AI总结本文构建了多模态基准测试Diagram-MMU，评估MLLMs的科学图表解析与理解能力，发现图表转代码任务更具挑战，Claude-4.6 Opus在智能体场景下表现最优。

2608.11234 2026-08-13 cs.AI cs.OS 新提交 70%

InfraBench: Evaluating Infrastructure Agents Across Layers, Lifecycle, and Risk

InfraBench：评估跨层级、全生命周期与风险的基础设施智能体

Yuan Gao, Zeren Yang, Junnan Li, Shawn, Zhong, Ahmed Dajani, Mai Zheng, Andrea Arpaci-Dusseau, Remzi Arpaci-Dusseau

机构 * University of Wisconsin–Madison（威斯康星大学麦迪逊分校）； Iowa State University（爱荷华州立大学）

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

AI总结针对AI智能体应对真实基础设施复杂度能力不明的问题，提出跨全系统栈、全生命周期且支持细粒度风险评估的InfraBench基准套件，实验表明现有最强智能体仍存在多方面失败模式。

Comments 17 pages, 6 figures. Preprint

2607.11175 2026-08-13 cs.AI 版本更新 70%

The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy

自我进化临床系统之路：将医疗智能体从辅助扩展到自主

Chunzheng Zhu, Lei Tian, Bohan Tan, Ziqi Zhou, Yuxuan Sun, Yijun Wang, Chengchao Lv, Yilin Wen, Yijun He, Jinghao Lin, Yihang Chen, Chee Wei Tan, Qianshan Wei, Lei Zhao, Bin Pu, Kenli Li, Yuan Xue, Jianxin Lin

机构 * Hunan University（湖南大学）； ByteDance（字节跳动）； Duke University（杜克大学）； Westlake University（西湖大学）； The University of Hong Kong（香港大学）； Nanyang Technological University（南洋理工大学）； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）； University of Macau（澳门大学）； The Ohio State University（俄亥俄州立大学）

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

AI总结研究探讨大语言模型等对医疗智能体的重塑，从临床部署出发，将其形式化为决策系统并给出自主性分类。沿统一框架扩展，强调临床环境扩展为关键方向，定位临床自我进化为前沿，还研究了多领域应用及挑战，提供医学成像系统路线图。

Comments Project page: https://github.com/zhcz328/Awesome-Medical-Agents

1. Agent评测 15729 篇

An Agent-Based Intrusion Detection System for Local Area Networks

Automatic Trading Agent. RMT based Portfolio Theory and Portfolio Selection

Illusory versus Genuine Control in Agent-Based Games

Temporal Effects of Agent Aggregation in the Dynamics of Multiagent Systems

Heterogeneity and feedback in an agent-based market model

Logical tools for handling change in agent-based systems

Price return auto-correlation and predictability in agent-based models of financial markets

Real payoffs and virtual trading in agent based market models

The value of information in financial markets: An agent-based simulation

Statistical properties of agent-based market area model

Cycles, determinism and persistence in agent-based games and financial time-series

Simulating non-small cell lung cancer with a multiscale agent-based model

Emergent Behavior in Agent Networks: Self-Organization in Wasp and Open Source Communities

RRL: A Rich Representation Language for the Description of Agent Behaviour in NECA

Evolution of heterogeneity in an agent-based market model

Strategic updating of threshold response in an agent-based market model

Turbulence as an Organizing Agent in the ISM

Bubbles, crashes and intermittency in agent based market models

Diffusion and Aggregation in an Agent Based Model of Stock Market Fluctuations

Volatility and Agent Adaptability in a Self-Organizing Market

Logic: A Misleading Concept. A Contradiction Study toward Agent's Logic

Agent trade servers in financial exchange systems

A Framework and Method for Online Inverse Reinforcement Learning

Inadvertent Context Leakage in Language Models

One Success Isn't Reliability: Thinkingbox, a Sandbox and Benchmark for Agents in Stateful Business Workflows

Symposium: Trust via Auditable Records for Communities of AI Scientist Agents

SysEvolve: An AI-native, safe, autonomous adversarial attack-defense co-evolutionary system

Diagram-MMU: A Multi-Modal Benchmark for Scientific Diagrams

InfraBench: Evaluating Infrastructure Agents Across Layers, Lifecycle, and Risk

The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy