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 597 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 其他Agent 597 篇

2601.06456 2026-01-13 cs.SE 57%

Architecting AgentOps Needs CHANGE

构建 AgentOps 需要 CHANGE

Shaunak Biswas, Hiya Bhatt, Karthik Vaidhyanathan

专题命中 其他Agent :agentic(abstract);分类 cs.SE

AI总结 本文提出CHANGE框架,用于构建能够适应不确定性和持续演化的AgentOps平台,以管理演进中的代理式人工智能系统。

Comments This paper has been accepted to CAIN 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.00738 2026-01-01 econ.GN cs.AI cs.CY q-fin.EC 57%

Orchestrating Rewards in the Era of Intelligence-Driven Commerce

在智能驱动商业时代 orchestrate 奖励

Paul Osemudiame Oamen, Robert Wesley, Pius Onobhayedo

机构 * My AI Inc. School of Natural and Computing Sciences, University of Aberdeen(自然与计算科学学院,阿伯丁大学) Marshall School of Business, University of Southern California(马歇尔商学院,南加州大学)

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

AI总结 本文提出一种混合框架,使品牌在保持主权控制的同时实现跨品牌互操作性,通过信任less交换机制解决传统联盟计划的结构性问题,并推导出数学定价模型以实现公平价值交换。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.17952 2025-12-23 cs.GT cs.AI econ.TH 57%

Will AI Trade? A Computational Inversion of the No-Trade Theorem

AI是否会交易?对无交易定理的计算反向分析

Hanyu Li, Xiaotie Deng

机构 * Peking University(北京大学) School of Computer Science(计算机科学学院) CFCS(计算机科学与技术系)

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

AI总结 本文研究了在共同信念下,AI代理由于计算限制可能导致无法达到均衡,从而产生更活跃的交易环境。

Comments Accepted in WINE 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.15732 2025-12-19 q-fin.TR cs.LG cs.NE q-fin.CP 57%

The Red Queen's Trap: Limits of Deep Evolution in High-Frequency Trading

红皇后陷阱:高频交易中深度进化局限性

Yijia Chen

机构 * Independent Researcher(独立研究者)

专题命中 其他Agent :autonomous agent(abstract);分类 cs.LG

AI总结 本文研究了高频交易中深度进化方法的局限性,发现模型复杂性增加在缺乏信息不对称时会加剧系统脆弱性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.02665 2025-12-03 cs.CL 57%

Input Order Shapes LLM Semantic Alignment in Multi-Document Summarization

输入顺序影响多文档摘要中LLM语义对齐

Jing Ma

机构 * University of Zurich(苏黎世大学)

专题命中 其他Agent :agentic(abstract);分类 cs.CL

AI总结 研究发现输入顺序显著影响LLM在多文档摘要中的语义对齐,优先位置的文章对摘要的语义相似性有显著影响。

Comments 9 pages, 3 figures, 2 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.20494 2025-12-02 cs.CL 57%

Adversarial Confusion Attack: Disrupting Multimodal Large Language Models

对抗混淆攻击:破坏多模态大语言模型

Jakub Hoscilowicz, Artur Janicki

机构 * Warsaw University of Technology(华沙技术大学)

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

AI总结 本文提出对抗混淆攻击,通过生成扰动破坏多模态大语言模型的可靠性,展示其在不同模型上的有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15534 2025-11-20 cs.AI 57%

Exploring the use of AI authors and reviewers at Agents4Science

探索AI作者和评审员在Agents4Science中的应用

Federico Bianchi, Owen Queen, Nitya Thakkar, Eric Sun, James Zou

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

AI总结 本文探讨了AI代理在科学领域作为作者和评审员的可行性,通过Agents4Science会议展示了人机协作在科研中的新模式。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.22084 2025-10-28 cs.CL 57%

Compositional Bias Control in Large Language Models: Preference Learning Fails, Supervision Succeeds

Atij Mahesh

机构 * University of California, Los Angeles(加州大学洛杉矶分校)

专题命中 其他Agent :agentic(abstract);分类 cs.CL

Comments 20 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.06314 2025-10-27 cs.CY cs.AI 57%

A4L: An Architecture for AI-Augmented Learning

Ashok Goel, Ploy Thajchayapong, Vrinda Nandan, Harshvardhan Sikka, Spencer Rugaber

机构 * Design Intelligence Laboratory, Georgia Institute of Technology(设计智能实验室,佐治亚理工学院)

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

Comments 14 pages, 7 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.18911 2025-10-23 physics.chem-ph cs.AI 57%

Prospects for Using Artificial Intelligence to Understand Intrinsic Kinetics of Heterogeneous Catalytic Reactions

Andrew J. Medford, Todd N. Whittaker, Bjarne Kreitz, David W. Flaherty, John R. Kitchin

机构 * organization= School of Chemical \& Biomolecular Engineering, Georgia Institute of Technology , addressline= 311 Ferst Drive NW , city= Atlanta , postcode= 30332 , state= GA , country= USA organization= Department of Chemical Engineering, Carnegie Mellon University , addressline= 5000 Forbes Street , city= Pittsburgh , postcode= 15213 , state= PA , country= USA

专题命中 其他Agent :agentic(abstract);分类 cs.AI

Comments Submitted to "Current Opinion in Chemical Engineering" for peer review

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13011 2025-10-16 cs.HC cs.AI 57%

Deliberate Lab: A Platform for Real-Time Human-AI Social Experiments

Crystal Qian, Vivian Tsai, Michael Behr, Nada Hussein, Léo Laugier, Nithum Thain, Lucas Dixon

机构 * Google DeepMind(谷歌DeepMind) Google(谷歌) EPFL(苏黎世联邦理工学院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05378 2025-10-08 cs.AI cs.HC 57%

What Do You Mean? Exploring How Humans and AI Interact with Symbols and Meanings in Their Interactions

Reza Habibi, Seung Wan Ha, Zhiyu Lin, Atieh Kashani, Ala Shafia, Lakshana Lakshmanarajan, Chia-Fang Chung, Magy Seif El-Nasr

机构 * University of California, Santa Cruz(加州大学圣克鲁兹分校)

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

Comments CHI 2026 Papers

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.01451 2025-10-03 q-fin.GN cs.LG 57%

Financial Stability Implications of Generative AI: Taming the Animal Spirits

Anne Lundgaard Hansen, Seung Jung Lee

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.12543 2025-09-24 cs.CL 57%

Disambiguation in Conversational Question Answering in the Era of LLMs and Agents: A Survey

Md Mehrab Tanjim, Yeonjun In, Xiang Chen, Victor S. Bursztyn, Ryan A. Rossi, Sungchul Kim, Guang-Jie Ren, Vaishnavi Muppala, Shun Jiang, Yongsung Kim, Chanyoung Park

机构 * Adobe Research(Adobe研究部) KAIST(韩国科学技术院) Adobe Inc.(Adobe公司)

专题命中 其他Agent :agentic(abstract);分类 cs.CL

Comments 14 pages, 2 figures, Accepted at EMNLP 2025 Main Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2405.04760 2025-09-23 cs.CR cs.AI 57%

Large Language Models for Cyber Security: A Systematic Literature Review

Hanxiang Xu, Shenao Wang, Ningke Li, Kailong Wang, Yanjie Zhao, Kai Chen, Ting Yu, Yang Liu, Haoyu Wang

机构 * Huazhong University of Science and Technology(华中科技大学) Hamad Bin Khalifa University(哈马德·本·卡伊夫大学) Nanyang Technological University(南洋理工大学)

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

Comments Accepted by ACM Transactions on Software Engineering and Methodology (TOSEM)

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.12849 2025-09-17 cs.DC cs.AI 57%

AI Factories: It's time to rethink the Cloud-HPC divide

Pedro Garcia Lopez, Daniel Barcelona Pons, Marcin Copik, Torsten Hoefler, Eduardo Quiñones, Maciej Malawski, Peter Pietzutch, Alberto Marti, Thomas Ohlson Timoudas, Aleksander Slominski

机构 * ETH(苏黎世联邦理工学院) IBM Research(IBM研究院)

专题命中 其他Agent :agentic(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2509.02144 2025-09-03 cs.HC cs.AI 57%

A Theoretical Framework of the Processes of Change in Psychotherapy Delivered by Artificial Agents

Arthur Bran Herbener, Malene Flensborg Damholdt

机构 * Department of Psychology and Behavioral Sciences(心理学与行为科学系)

专题命中 其他Agent :agentic(abstract);分类 cs.AI

Comments Submitted on 19 March 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.21368 2025-09-01 econ.GN cs.AI q-fin.EC 57%

EconAgentic in DePIN Markets: A Large Language Model Approach to the Sharing Economy of Decentralized Physical Infrastructure

Yulin Liu, Mocca Schweitzer

机构 * Quantum Economics Zug Switzerland(量子经济学研究所)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.18563 2025-08-27 cs.CY cs.AI 57%

The Quasi-Creature and the Uncanny Valley of Agency: A Synthesis of Theory and Evidence on User Interaction with Inconsistent Generative AI

Mauricio Manhaes, Christine Miller, Nicholas Schroeder

专题命中 其他Agent :agentic(abstract);分类 cs.AI

Comments 33 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.13960 2025-08-20 cs.GT cs.AI 57%

A Mechanism for Mutual Fairness in Cooperative Games with Replicable Resources -- Extended Version

Björn Filter, Ralf Möller, Özgür Lütfü Özçep

机构 * Institute for Humanities-Centered AI (CHAI), University of Hamburg, Germany(人文中心人工智能研究所(CHAI),汉堡大学)

专题命中 其他Agent :agentic(abstract);分类 cs.AI

Comments This paper is the extended version of a paper accepted at the European Conference on Artificial Intelligence 2025 (ECAI 2025), providing the proof of the main theorem in the appendix

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.05619 2025-08-08 cs.AI nlin.AO physics.bio-ph physics.comp-ph physics.hist-ph 57%

The Missing Reward: Active Inference in the Era of Experience

Bo Wen

机构 * IBM T.J. Watson Research Center(IBM TJ沃森研究中心)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.05152 2025-08-08 cs.IR cs.AI 57%

Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Models

Linfeng Gao, Yaoxiang Wang, Minlong Peng, Jialong Tang, Yuzhe Shang, Mingming Sun, Jinsong Su

机构 * School of Informatics, Xiamen University(厦门大学信息学院) Baidu(百度) Alibaba(阿里巴巴)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.09041 2025-07-15 cs.LG cs.RO cs.SY eess.SY 57%

Behavioral Exploration: Learning to Explore via In-Context Adaptation

Andrew Wagenmaker, Zhiyuan Zhou, Sergey Levine

机构 * Department of Electrical Engineering \& Computer Science, University of California, Berkeley

专题命中 其他Agent :autonomous agent(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.03050 2025-07-08 cs.CY cs.AI 57%

From Turing to Tomorrow: The UK's Approach to AI Regulation

Oliver Ritchie, Markus Anderljung, Tom Rachman

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

Comments This is a chapter intended for publication in a forthcoming edited volume. It is the version of the author's manuscript prior to acceptance for publication and has not undergone editorial and/or peer review on behalf of the Publisher

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.02103 2025-07-04 cs.AI q-bio.NC 57%

What Neuroscience Can Teach AI About Learning in Continuously Changing Environments

Daniel Durstewitz, Bruno Averbeck, Georgia Koppe

专题命中 其他Agent :agentic(abstract);分类 cs.AI

Comments Submitted as a Perspective article (10 pages, 5 figures)

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.01060 2025-07-03 cs.IR cs.LG 57%

Optimizing Conversational Product Recommendation via Reinforcement Learning

Kang Liu

机构 * Independent Researcher(独立研究者)

专题命中 其他Agent :agentic(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2505.23153 2025-07-02 cs.AI 57%

Conceptual Framework Toward Embodied Collective Adaptive Intelligence

Fan Wang, Shaoshan Liu

机构 * Shenzhen Institute of Artificial Intelligence and Robotics for Society(深圳人工智能与机器人研究院)

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.12245 2025-06-17 cs.AI 57%

Reversing the Paradigm: Building AI-First Systems with Human Guidance

Cosimo Spera, Garima Agrawal

机构 * Minerva CQ

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

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.07281 2025-06-10 cs.HC cs.AI 57%

Secondary Stakeholders in AI: Fighting for, Brokering, and Navigating Agency

Leah Hope Ajmani, Nuredin Ali Abdelkadir, Stevie Chancellor

机构 * University of Minnesota(明尼苏达大学)

专题命中 其他Agent :agentic(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2506.03755 2025-06-05 cs.CY cs.AI 57%

Misalignment or misuse? The AGI alignment tradeoff

Max Hellrigel-Holderbaum, Leonard Dung

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

Comments Forthcoming in Philosophical Studies

详情

展开后加载摘要…

URL PDF HTML 收藏