Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI
CERN（欧洲核子研究中心）
Lorenzo Giusti, Ole Anton Werner, Riccardo Taiello, Matilde Carvalho Costa, Emre Tosun, Andrea Protani, Marc Molina, Rodrigo Lopes de Almeida, Paolo Cacace, Dio… 展开作者
Lorenzo Giusti, Ole Anton Werner, Riccardo Taiello, Matilde Carvalho Costa, Emre Tosun, Andrea Protani, Marc Molina, Rodrigo Lopes de Almeida, Paolo Cacace, Diogo Reis Santos, Luigi Serio
我们提出了智能体联邦（Federation of Agents, FoA），一种分布式编排框架，将静态的多智能体协调转变为动态的、基于能力的协作。FoA引入了版本化能力向量（Versioned Capability Vectors, VCVs）：一种机器可读的配置文件，通过语义嵌入使智能体能力可被搜索，从而使智能体能够宣传其能力、成本和局限性。我们的架构结合了三个关键创新：（1）语义路由，通过分片HNSW索引将任务与智能体匹配，并通过成本偏置优化来强制执行操作约束；（2）动态任务分解，其中兼容的智能体通过基于共识的合并，协作将复杂任务分解为子任务的DAG（有向无环图）；（3）智能聚类，将处理相似子任务的智能体分组到协作通道中，进行k轮细化后再综合。FoA构建于MQTT的发布-订阅语义之上，以实现可扩展的消息传递，通过层次化能力匹配和高效的索引维护实现次线性复杂度。在HealthBench上的评估显示，与单模型基线相比，性能提升了13倍，其中聚类增强的协作对于需要多视角的复杂推理任务尤为有效。该系统可水平扩展，同时保持一致的性能，表明带有结构化协作的语义编排能够释放异构AI智能体联邦的集体智能。
英文摘要：
We present Federation of Agents (FoA), a distributed orchestration framework that transforms static multi-agent coordination into dynamic, capability-driven collaboration. FoA introduces Versioned Capability Vectors (VCVs): machine-readable profiles that make agent capabilities searchable through semantic embeddings, enabling agents to advertise their capabilities, cost, and limitations. Our aarchitecturecombines three key innovations: (1) semantic routing that matches tasks to agents over sharded HNSW indices while enforcing operational constraints through cost-biased optimization, (2) dynamic task decomposition where compatible agents collaboratively break down complex tasks into DAGs of subtasks through consensus-based merging, and (3) smart clustering that groups agents working on similar subtasks into collaborative channels for k-round refinement before synthesis. Built on top of MQTT,s publish-subscribe semantics for scalable message passing, FoA achieves sub-linear complexity through hierarchical capability matching and efficient index maintenance. Evaluation on HealthBench shows 13x improvements over single-model baselines, with clustering-enhanced laboration particularly effective for complex reasoning tasks requiring multiple perspectives. The system scales horizontally while maintaining consistent performance, demonstrating that semantic orchestration with structured collaboration can unlock the collective intelligence of heterogeneous federations of AI agents.
6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence
Department of Computer and Network Engineering, United Arab Emirates University, UAE（计算机与网络工程系，阿联酋大学）；Research Institute for Digital Future, Khalifa University, UAE（数字未来研究院，哈利法大学）
Bridging the Cognitive Gap: A Unified Memory Paradigm for 6G Agentic AI-RAN
Sun Yat-sen University, China（中山大学，中国）；Zhejiang University, China（浙江大学，中国）；University of Exeter, U.K.（埃克塞特大学，英国）；Singapore University of Technology and Design, Singapore（新加坡科技设计大学，新加坡）；Purple Mountain Laboratories, Nanjing, China（紫金山实验室，南京，中国）
A Blockchain-Monitored Agentic AI Architecture for Trusted Perception-Reasoning-Action Pipelines
Faculty of Computer Studies, Arab Open University-Bahrain（巴林阿拉伯开放大学计算机科学学院）；Faculty of Computer and Information System, Islamic University of Madinah, Saudi Arabia（沙特阿拉伯麦地那伊斯兰大学计算机与信息系统学院）
BrainPilot: Automating Brain Discovery with Agentic Research
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）
DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation
Department of Mechanical Engineering, University of Michigan, Ann Arbor, Michigan, USA（机械工程系，密歇根大学，安阿伯，密歇根州，美国）；Max-Planck-Institute for Sustainable Materials, Materials Informatics, Düsseldorf, Germany（可持续材料研究所，材料信息学，杜塞尔多夫，德国）；Mechanical Engineering, University of Michigan, Ann Arbor, Michigan, USA（机械工程，密歇根大学，安阿伯，密歇根州，美国）
Hallucination Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching
Head of AI, Tesisquare Member, Open Voice Interoperability Initiative Linux Foundation AI & Data（AI负责人，Tesisquare成员，开放语音互操作性倡议Linux基金会AI与数据）；Principal, Conversational Technologies Member, Open Voice Interoperability Initiative Linux Foundation AI & Data（首席科学家，对话技术成员，开放语音互操作性倡议Linux基金会AI与数据）
MDGYM: Benchmarking AI Agents on Molecular Simulations
Yardi School of Artificial Intelligence, Indian Institute of Technology Delhi（印度理工学院德里人工智能学院）；Department of Computer Science and Engineering, Indian Institute of Technology Delhi（印度理工学院德里计算机科学与工程系）；Department of Civil and Environmental Engineering, Indian Institute of Technology Delhi（印度理工学院德里土木与环境工程系）
Safety Signals to Verify NetOps Agents with Action-Level Granularity
Fraunhofer Heinrich-Hertz-Institut（弗劳恩霍夫海因里希-赫兹研究所）；Nokia Bell Laboratories（诺基亚贝尔实验室）；Technische Universität Berlin（柏林工业大学）；BIFOLD – Berlin Institute for the Foundations of Learning and Data（BIFOLD – 柏林学习与数据基础研究所）
How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfare
Department of Sustainable Communication Technologies, SINTEF Digital（可持续通信技术系，SINTEF数字）；Max Planck Institute for Security and Privacy（安全与隐私研究所）；Department of Mathematics, City St George’s University of London（数学系，圣乔治大学）；Macrostrategy Research Initiative（战略研究计划）；Human Nature Lab, Yale University（人性实验室，耶鲁大学）；Department of Politics and Public Administration, University of Konstanz（政治与公共管理系，康斯坦茨大学）；Harvard Business School, Harvard University（哈佛商学院，哈佛大学）；Department of Psychology, University of Cambridge（心理学系，剑桥大学）；Department of Computer Science, University of British Columbia（计算机科学系，不列颠哥伦比亚大学）；Department of Human Centered Design & Engineering, University of Washington（以人为本设计与工程系，华盛顿大学）；Department of Psychology, New York University（心理学系，纽约大学）；Observatory on Social Media and Luddy School of Informatics, Computing, and Engineering, Indiana University（社交媒体观察所和信息、计算与工程学院，印第安纳大学）
