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 14777 信号源:cs.AI, cs.CL, cs.LG, cs.SE

1. 多智能体 14777 篇

2511.15755 2026-01-08 cs.AI cs.SE 89%

Multi-Agent LLM Orchestration Achieves Deterministic, High-Quality Decision Support for Incident Response

多智能体大语言模型协调实现确定性、高质量的事件响应决策支持

Philip Drammeh

机构 * Philip Drammeh, M.Eng(菲利普·德拉梅, 工程硕士)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.SE

AI总结 多智能体大语言模型协调显著提升事件响应的确定性和质量,实现100%可操作建议率,为生产环境提供可靠决策支持。

Comments 10 pages, 4 tables. v2: Expanded limitations, added threats to validity, clarified agent definition, added reproducibility notes, updated Phase 2 timeline with current models (GPT-5.2, Claude Sonnet 4.5, Llama 3.3 70B). No changes to experimental results

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.20629 2026-01-06 cs.LG cs.AI 89%

Learning Evolving Latent Strategies for Multi-Agent Language Systems without Model Fine-Tuning

为多智能体语言系统学习演化的潜在策略而无需模型微调

Wenlong Tang

机构 * Independent Researcher(独立研究者)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

AI总结 该研究提出一种无需微调的多智能体语言系统框架,通过双环架构实现持续策略进化,利用外部潜在空间提供可解释的抽象战略表示。

Comments 17 pages, 5 figures. Code available at https://github.com/wltang-dev/Latent-Strategy-RL-Agent

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.05158 2025-10-08 cs.AI cs.CE cs.LG cs.MA 89%

Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework

Xin He, Liangliang You, Hongduan Tian, Bo Han, Ivor Tsang, Yew-Soon Ong

机构 * Agency for Science, Technology and Research (A*STAR)(科技研究局) Hong Kong Baptist University(香港 Baptist 大学) North China Electric Power University(华北电力大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

Comments PINN, PDE, Agent, LLM

详情

展开后加载摘要…

URL PDF HTML 收藏
2312.11768 2023-12-20 cs.AI cs.LG cs.MA 89%

Curriculum Learning for Cooperation in Multi-Agent Reinforcement Learning

Rupali Bhati, Sai Krishna Gottipati, Clodéric Mars, Matthew E. Taylor

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

Comments 9 pages, 5 figures. Presented at Agent Learning in Open-Endedness Workshop at Neural Information Processing Systems (NeurIPS 2023)

详情

展开后加载摘要…

URL PDF HTML 收藏
2207.02249 2023-11-21 cs.MA cs.AI cs.LG 89%

Learning Task Embeddings for Teamwork Adaptation in Multi-Agent Reinforcement Learning

Lukas Schäfer, Filippos Christianos, Amos Storkey, Stefano V. Albrecht

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG;planning(comments)

Comments To be presented at the Seventh Workshop on Generalization in Planning at the NeurIPS 2023 conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2302.10418 2023-03-01 cs.LG cs.AI cs.MA 89%

MAC-PO: Multi-Agent Experience Replay via Collective Priority Optimization

Yongsheng Mei, Hanhan Zhou, Tian Lan, Guru Venkataramani, Peng Wei

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG;autonomous agent(comments)

Comments The 22nd International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023). arXiv admin note: text overlap with arXiv:2302.05593

详情

展开后加载摘要…

URL PDF HTML 收藏
2207.02007 2022-07-08 cs.LG cs.AI 89%

The StarCraft Multi-Agent Challenges+ : Learning of Multi-Stage Tasks and Environmental Factors without Precise Reward Functions

Mingyu Kim, Jihwan Oh, Yongsik Lee, Joonkee Kim, Seonghwan Kim, Song Chong, Se-Young Yun

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG

Comments ICML Workshop: AI for Agent Based Modeling 2022 Spotlight

详情

展开后加载摘要…

URL PDF HTML 收藏
2008.05214 2022-02-08 cs.LG cs.AI cs.MA stat.ML 89%

REMAX: Relational Representation for Multi-Agent Exploration

Heechang Ryu, Hayong Shin, Jinkyoo Park

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG;autonomous agent(comments)

Comments Accepted as a full paper at the Twenty-First International Conference on Autonomous Agents and Multiagent Systems (AAMAS-22), Virtual Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2201.11994 2022-02-01 cs.RO cs.AI cs.LG cs.MA 89%

FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems

Yutong Wang, Guillaume Sartoretti

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG;autonomous agent(comments)

Comments To appear in the International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2022)

详情

展开后加载摘要…

URL PDF HTML 收藏
2102.04402 2021-12-06 cs.LG cs.AI 89%

Contrasting Centralized and Decentralized Critics in Multi-Agent Reinforcement Learning

Xueguang Lyu, Yuchen Xiao, Brett Daley, Christopher Amato

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG;autonomous agent(journal_ref)

Journal ref Proceedings of the 20th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS). 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.01129 2021-05-05 cs.AI cs.CL cs.CV cs.MA 89%

Towards A Multi-agent System for Online Hate Speech Detection

Gaurav Sahu, Robin Cohen, Olga Vechtomova

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.CL;autonomous agent(comments)

Comments Accepted to the 2nd International Workshop on Autonomous Agents for Social Good (AASG), AAMAS, 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2102.00582 2021-02-10 cs.AI cs.LG cs.LO cs.MA 89%

Multi-Agent Reinforcement Learning with Temporal Logic Specifications

Lewis Hammond, Alessandro Abate, Julian Gutierrez, Michael Wooldridge

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG;autonomous agent(comments)

Comments Accepted to the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-21)

详情

展开后加载摘要…

URL PDF HTML 收藏
2101.06890 2021-01-19 cs.LG cs.AI cs.MA 89%

Cooperative and Competitive Biases for Multi-Agent Reinforcement Learning

Heechang Ryu, Hayong Shin, Jinkyoo Park

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI、cs.LG;autonomous agent(comments)

Comments Accepted as a full paper at the Twentieth International Conference on Autonomous Agents and Multiagent Systems (AAMAS-21), Virtual Conference

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.14587 2026-08-18 cs.AI 新提交 89%

An Agentic Framework Using Rules and LLMs for Embedding and Annotating Descriptive Document Layouts: A Plant Science Use Case

一种结合规则与大语言模型(LLM)的智能体框架,用于描述性文档布局的嵌入与标注:植物科学应用案例

Nicolas Turenne, Youcef Sklab, Eric Chenin, Jean-Daniel Zucker

专题命中 多智能体 :agentic(title,abstract);agent(abstract);tool use(abstract);planning(abstract)

AI总结 本研究提出结合规则与LLM的智能体框架,用于植物性状提取,在三个区域植物数据集上实现高效标注,提升了性状覆盖度与标注量,验证了其稳健性与可扩展性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.07651 2026-08-11 cs.AI cs.CV 新提交 89%

An Agentic AI Framework Overcomes Fundamental Limitations of Large Language Models for Glaucoma Detection from Fundus Photography

一种智能体AI框架克服了大型语言模型在眼底照相青光眼检测中的基本局限

Jalil Jalili, Hossein Taghizad, Anuwat Jiravarnsirikul, Christopher Bowd, Akram Belghith, Raheleh Kafieh, Christopher A. Girkin, Sally L. Baxter, Robert N. Weinreb, Linda M. Zangwill, Mark Christopher

专题命中 多智能体 :agentic(title,abstract);agent(abstract);workflow(abstract);function calling(abstract)

AI总结 该研究开发的智能体AI框架整合LLM与专用深度学习工具,提升了眼底照相青光眼检测的准确率、一致性,纠正了仅用LLM的缺陷,具有通用性,或推动医学AI向多智能体系统转变。

详情

展开后加载摘要…

URL PDF HTML 收藏
2608.05792 2026-08-07 cs.AI 新提交 89%

When Agentic AI Meets Integrated Sensing and Communication

当智能体AI遇上集成感知与通信

Kai Li, Conggai Li, Sarah Ali Siddiqui, Syed Sohail Ahmed, Xin Yuan, Shenghong Li, Wei Ni

机构 * University of Luxembourg(卢森堡大学) CSIRO(联邦科学与工业研究组织) Qassim University(卡西姆大学) Edith Cowan University(伊迪丝·考恩大学)

专题命中 多智能体 :agentic(title,abstract);agent(abstract);tool use(abstract);planning(abstract)

AI总结 本综述提出智能体AI与集成感知通信结合的AISAC范式,构建六阶段闭环框架与五成熟度等级,梳理相关领域进展,分析交叉需求,发现现有系统智能体成熟度不足,并指出多方面开放挑战。

Comments 35 pages, 132 references, 10 tables, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.22319 2026-07-27 cs.DB cs.AI 新提交 89%

Towards Trustworthy and Cost-Efficient Data Integration: From Naïve RAG to Agentic RAG

迈向可信且经济高效的数据集成:从朴素检索增强生成到智能体检索增强生成

Chuangtao Ma, Arijit Khan

机构 * Aalborg University, Denmark(丹麦奥胡斯大学) Bowling Green State University, USA(美国布恩威尔州立大学)

专题命中 多智能体 :agentic(title,abstract);agent(abstract);AI agent(abstract);workflow(abstract)

AI总结 探讨大语言模型和人工智能智能体在企业数据集成中面临的挑战,介绍从经典RAG到智能体RAG的演变,研究经济高效集成的优化策略,为构建可靠、可解释和可扩展的数据集成系统指明方向。

Comments To Appear in the IEEE Data Engineering Bulletin

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.15079 2026-07-20 cs.AI 版本更新 89%

BrainPilot: Automating Brain Discovery with Agentic Research

BrainPilot:通过智能研究实现大脑发现自动化

Haoxuan Li, Tianci Gao, Jianhe Li, Yang Fan, Runze Shi, Weiran Wang, Tianxiang Zhao, Zezhao Wu, Xiaoyang Jiang, Qihui Zhang, Jia Li, Xiao Xiao, Kai Du, Xiaoxuan Jia, Chao Xie, Lu Mi

机构 * College of AI, Tsinghua University(清华大学人工智能学院) Shanghai Qizhi Institute(上海期智研究院) Business School, Renmin University of China(中国人民大学商学院) School of Physics, Beihang University(北京航空航天大学物理学院) School of Information and Software Engineering, University of Electronic Science and Technology of China(电子科技大学信息与软件工程学院) Behavioral and Cognitive Neuroscience Center, Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University(复旦大学脑科学与智能技术研究院行为与认知神经科学中心) College of Engineering, Georgia Institute of Technology(佐治亚理工学院工程学院) School of Life Sciences & IDG/McGovern Institute for Brain Research, Tsinghua University(清华大学生命科学学院&清华-IDG/麦戈文脑科学研究院) School of Computing and Artificial Intelligence, Southwest Jiaotong University(西南交通大学计算机与人工智能学院) Weixian College, Tsinghua University(清华大学未央学院) Department of Psychological and Cognitive Sciences, Tsinghua University(清华大学心理学与认知科学系)

专题命中 多智能体 :agentic(title);agent(abstract);AI agent(abstract);tool use(abstract)

AI总结 研究针对脑科学研究整合证据难、人工智能代理有缺陷的问题,提出完全开源的多智能体系统BrainPilot,它有可追溯日志和验证结果,含知识库与技能库,经实验评估,其开源模型以低成本达先进框架性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.12051 2026-07-15 cs.CL 新提交 89%

Agentic systems for breast cancer treatment recommendations

用于乳腺癌治疗建议的智能体系统

Vinicius Anjos de Almeida, Nícolas Henrique Borges, Leonardo Vicenzi, Helena Kociolek, Sarah Miriã de Castro Rocha, Frederico Nassif Gomes, Júlia Cristina Ferreira Ribeiro, Lucas Emanuel Silva e Oliveira

机构 * Spesia(斯佩西亚) Faculdade de Medicina, Universidade de São Paulo(圣保罗大学医学院) Laboratory of Artificial Intelligence Applied to Bioinformatics, SEPT, Universidade Federal do Paraná (UFPR)(巴拉那联邦大学人工智能应用于生物信息学实验室,SEPT) Pontifícia Universidade Católica do Paraná (PUCPR)(巴拉那天主大学)

专题命中 多智能体 :agentic(title,abstract);agent(abstract);tool use(abstract);planning(abstract)

AI总结 研究评估用于乳腺癌治疗建议的智能体LLM系统,用72个真实临床病例和1147个特定病例量表,比较七种流程,最佳配置全局得分为0.594±0.025,工具使用和智能体自主性影响各异,虽能生成相关建议,但用于无监督临床使用仍不足。

Comments Under peer review. Source code available at: https://github.com/GRUPOMED4U/breast_cancer_agents_paper

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.14130 2026-07-13 cs.LG cs.MA 新提交 89%

Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning

基于合约的组合屏蔽实现安全多智能体强化学习

Omar Adalat, Edwin Hamel-De le Court, Francesco Belardinelli

机构 * Imperial College London(伦敦帝国学院) University of Manchester(曼彻斯特大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.LG

AI总结 提出一种去中心化屏蔽方法,通过合约机制协调智能体局部LTL安全义务,在无集中运行时控制下保证全局安全并优化团队奖励。

Comments Accepted to EUMAS 2026, the 23rd European Conference on Multi-Agent Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.01425 2026-07-07 cs.AI 新提交 89%

Agent4cs: A Multi-agent System for Code Summarization in Large Hierarchical Codebases

Agent4cs:面向大型分层代码库的代码摘要多智能体系统

Yongjian Tang, Ezgi Sarikayak, Doruk Tuncel, Jie M. Zhang, Thomas Runkler

机构 * Siemens AG(西门子股份公司) Technical University of Munich(慕尼黑工业大学) Kings College London(伦敦国王学院)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI

AI总结 提出多智能体框架Agent4cs,通过自底向上方式对大型代码库进行摘要,包含摘要、关键词提取和质量保证三个智能体,在语义一致性和关键词覆盖率上分别提升8%和38%。

Comments Accepted to the main track of the 23rd European Conference on Multi-Agent Systems (EUMAS 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.25526 2026-06-25 cs.LG cs.MA 新提交 89%

Low Variance Trust Region Optimization with Independent Actors and Sequential Updates in Cooperative Multi-agent Reinforcement Learning

低方差信任区域优化:合作多智能体强化学习中的独立参与者与顺序更新

Bang Giang Le, Viet Cuong Ta

机构 * Human Machine Interaction Laboratory(人机交互实验室)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.LG

AI总结 针对合作多智能体强化学习中顺序更新导致优势函数方差指数级增长的问题,提出裁剪目标控制优势波动上限,实现亚线性收敛到ε-纳什均衡,并在三个基准测试中优于基线方法。

Journal ref utonomous Agents and Multi-Agent Systems 39.1 (2025): 12

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.03453 2026-06-03 cs.CR cs.AI cs.MA 89%

FORGE: Multi-Agent Graduated Exploitation and Detection Engineering

FORGE:多智能体渐进式利用与检测工程

Farooq Shaikh

机构 * Dynatrace

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI

AI总结 提出多智能体系统FORGE,通过渐进式利用深度桥接漏洞利用生成、优先级排序和检测规则工程三个孤立领域,在603个CVE上实现67.8%的端到端L1+利用,并生成低误报的Sigma和Snort检测规则。

Comments 18 pages, 4 figures, 3 tables. Accepted at the AgentCy Workshop at the 21st International Conference on Availability, Reliability and Security (ARES 2026). Keywords: Vulnerability assessment, Multi-agent systems, Exploit generation, Detection engineering, Risk prioritization

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.26521 2026-05-27 cs.SE 89%

Testing Agentic Workflows with Structural Coverage Criteria

使用结构覆盖标准测试智能体工作流

Nafiseh Kahani, Mojtaba Bagherzadeh

专题命中 多智能体 :agentic(title);AI agent(abstract,abstract_cn);agent(abstract);workflow(abstract)

AI总结 针对多智能体工作流的结构化测试问题,提出基于类型化协调图的覆盖驱动测试方法,通过DSPy生成可执行场景,有效检测工具访问、限制和委托路径的结构性回归。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.00360 2026-05-19 cs.MA cs.AI cs.CY 89%

Mapping Human Anti-collusion Mechanisms to Multi-agent AI Systems

将人类反串通机制映射到多智能体AI系统

Jamiu Idowu, Ahmed Almasoud, Ayman Alfahid

机构 * Sahel AI, Sahel Group Inc.(萨赫尔人工智能,萨赫尔集团有限公司) Prince Sultan University(普林斯顿国王大学) Majmaah University(马吉玛大学)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.AI

AI总结 本文研究如何将人类长期积累的反串通机制应用于多智能体AI系统,通过建立机制分类并提出实现方法,同时指出开放挑战如责任归属、身份流动性、边界问题和对抗性适应等。

Comments Accepted to ICML 2026 Workshop on Technical AI Governance Research (TAIGR); Published in Knowledge-Based Systems Journal

Journal ref Idowu, J., Almasoud, A. S., & Alfahid, A. (2026). Mapping human anti-collusion mechanisms to multi-agent AI systems. Knowledge-Based Systems, 344(116067), 116067. https://doi.org/10.1016/j.knosys.2026.116067

详情

展开后加载摘要…

URL PDF HTML 收藏
2602.15006 2026-05-13 cs.MA cs.LG math.DG 89%

Distributed Quantum Gaussian Processes for Multi-Agent Systems

分布式量子高斯过程用于多智能体系统

Meet Gandhi, George P. Kontoudis

机构 * Colorado School of Mines(科罗拉多理工学院)

专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);autonomous agent(comments,journal_ref);分类 cs.LG

AI总结 本文提出分布式量子高斯过程方法,通过量子计算提升多智能体系统的建模能力和扩展性,采用分布式共识黎曼交替方向乘子法解决非欧几里得优化问题。

Comments 9 pages, 4 figures, accepted at AAMAS 2026 (International Conference on Autonomous Agents and Multiagent Systems)

Journal ref 2026 International Conference on Autonomous Agents and Multiagent Systems

详情

展开后加载摘要…

URL PDF HTML 收藏
2512.22579 2026-05-13 cs.AI cs.NI 89%

SANet: A Semantic-aware Agentic AI Networking Framework for Cross-layer Optimization in 6G

SANet:一种面向6G跨层优化的语义感知代理AI网络框架

Yong Xiao, Xubo Li, Haoran Zhou, Yingyu Li, Yayu Gao, Guangming Shi, Ping Zhang, Marwan Krunz

机构 * the School of Electronic Information and Communications, the Huazhong University of Science and Technology, Wuhan, China(电子信息学院,华中科技大学,武汉,中国) the Peng Cheng Laboratory, Shenzhen, China(鹏城实验室,深圳,中国) the School of Mechanical Engineering and Electronic Information, China University of Geosciences (Wuhan), China(机械工程与电子信息学院,中国地质大学(武汉),中国) the State Key Laboratory of Networking and Switching(网络与交换技术国家重点实验室)

专题命中 多智能体 :agentic(title,abstract);agent(abstract);AI agent(abstract);multi-agent(abstract)

AI总结 本文提出SANet,一种语义感知的代理AI网络架构,通过推断用户语义目标并自动分配不同网络层的代理以实现目标,解决多代理多目标优化问题,实验显示性能提升达14.61%。

Comments Accepted at IEEE Transactions on Mobile Computing

Journal ref IEEE Transactions on Mobile Computing, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.05861 2026-05-08 cs.AI cs.NI 89%

SANEmerg: An Emergent Communication Framework for Semantic-aware Agentic AI Networking

SANEmerg: 一种面向语义感知代理AI网络的涌现通信框架

Yong Xiao, Haoran Zhou, Yujie Zhou, Marwan Krunz

机构 * 1 School of Elect. Inform. \& Commun., Huazhong Univ. of Science \& Technology, China 2 Peng Cheng Laboratory, Shenzhen, China 3 Pazhou Laboratory (Huangpu), Guangzhou, China 4 Department of Electrical Computer Engineering, the University of Arizona

专题命中 多智能体 :agentic(title,abstract);agent(abstract);AI agent(abstract);autonomous agent(abstract)

AI总结 本文提出SANEmerg框架,通过语义感知机制自动检测用户意图并分配子任务,提升大规模代理AI网络的通信效率与性能。

Comments Accepted at IEEE/IFIP WiOpt Workshop, Columbus, OH, USA, June 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.11548 2026-04-14 cs.AI 89%

SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering

SemaClaw:通过Harness工程迈向通用个人AI代理的一步

Ningyan Zhu, Huacan Wang, Jie Zhou, Feiyu Chen, Shuo Zhang, Ge Chen, Chen Liu, Jiarou Wu, Wangyi Chen, Xiaofeng Mou, Yi Xu

机构 * Midea AIRC(美的AIRC)

专题命中 多智能体 :AI agent(title,abstract);agent(abstract);planning(abstract);agentic(abstract)

AI总结 SemaClaw通过Harness工程推动个人AI代理发展,提出DAG-based两阶段混合代理团队编排方法、PermissionBridge行为安全系统、三级上下文管理架构和代理维基技能,提升AI代理的可控性与可扩展性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.07546 2026-04-10 cs.AI 89%

Agentic Copyright, Data Scraping & AI Governance: Toward a Coasean Bargain in the Era of Artificial Intelligence

代理版权、数据抓取与AI治理:迈向人工智能时代的科西斯谈判

Paulius Jurcys, Mark Fenwick

专题命中 多智能体 :agentic(title,abstract);agent(abstract);AI agent(abstract);autonomous agent(abstract)

AI总结 本文探讨多代理AI系统快速部署对版权法和创意市场基础的影响,提出代理版权模型,通过整合法律、技术与制度监督,解决自主代理间的协调、冲突和共谋问题,旨在恢复创意产业的市场秩序。

详情

展开后加载摘要…

URL PDF HTML 收藏