Agentic AI systems present both significant opportunities and novel risks due to their capacity for autonomous action, encompassing tasks such as code execution, internet interaction, and file modification. This poses considerable challenges for effective organizational governance, particularly in comprehensively identifying, assessing, and mitigating diverse and evolving risks. To tackle this, we introduce the Agentic Risk \& Capability (ARC) Framework, a technical governance framework designed to help organizations identify, assess, and mitigate risks arising from agentic AI systems. The framework's core contributions are: (1) it develops a novel capability-centric perspective to analyze a wide range of agentic AI systems; (2) it distills three primary sources of risk intrinsic to agentic AI systems - components, design, and capabilities; (3) it establishes a clear nexus between each risk source, specific materialized risks, and corresponding technical controls; and (4) it provides a structured and practical approach to help organizations implement the framework. This framework provides a robust and adaptable methodology for organizations to navigate the complexities of agentic AI, enabling rapid and effective innovation while ensuring the safe, secure, and responsible deployment of agentic AI systems. Our framework is open-sourced \href{https://govtech-responsibleai.github.io/agentic-risk-capability-framework/}{here}.
See, Hypothesize, Validate: Multimodal Agentic Framework for Discovering Governing PDEs
Indian Institute of Technology Delhi(印度德里理工学院);Robert Bosch GmbH(罗伯特·博世有限公司);TCS Research(塔塔咨询服务公司研究院);Yardi School of Artificial Intelligence (ScAI)(亚迪人工智能学院);Department of Applied Mechanics(应用力学系)
The Controllability Trap: A Governance Framework for Military AI Agents
MARS (Mentorship for Alignment Researchers) 4.0 Fellow(MARS(对齐研究导师计划)4.0 Fellow);Cambridge AI Safety Hub (CAISH) University of Cambridge(剑桥AI安全中心(CAISH)剑桥大学)
Integrated Design and Governance of Agentic AI Systems through Adaptive Information Modulation
Department of Mechanical and Industrial Engineering(机械与工业工程系);Institute of Experiential AI(体验人工智能研究所);Network Science Institute(网络科学研究所);Northeastern University(东北大学);Boston, MA 02115, United States(波士顿,马萨诸塞州,02115,美国)
Agentic AI Sustainability Assessment for Supply Chain Document Insights
Head of AI, Tesisquare(Tesisquare人工智能负责人);Voiceinteroperability.ai Initiative Member(Voiceinteroperability.ai项目成员);Linux Foundation AI & Data(Linux基金会人工智能与数据);Functional Analyst, Tesisquare(Tesisquare功能分析师);MSc in Engineering Management Polytechnic University of Turin(理工学院工程管理硕士);Assistant Professor in PM and Supply Chain Management Polytechnic University of Turin(理工学院项目管理与供应链管理副教授)
Agentic Business Process Management: A Research Manifesto
Free University of Bozen-Bolzano(博尔扎诺自由大学);University of Oxford(牛津大学);University of Tartu(塔尔图大学);IBM Research(IBM研究院);Umeå University(于默奥大学);paluno (Ruhr Institute for Software Technology), University of Duisburg Essen(帕卢诺(鲁尔软件技术研究所),杜伊斯堡-埃森大学);University of Ottawa(渥太华大学);German Research Center for Artificial Intelligence (DFKI)(德国人工智能研究中心(DFKI));Saarland University(萨尔大学);The University of Melbourne(墨尔本大学);TUM School of Computation, Information, and Technology, TU Munich(慕尼黑工业大学计算、信息与技术学院);RMIT University(皇家墨尔本理工大学);Meta;University of St. Gallen(圣加仑大学)
From Code-Centric to Intent-Centric Software Engineering: A Reflexive Thematic Analysis of Generative AI, Agentic Systems, and Engineering Accountability
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
Hong Kong University of Science and Technology(香港科学与技术大学);National University of Singapore(新加坡国立大学);University of Oxford(牛津大学);Nanyang Technological University(南洋理工大学);Chinese University of Hong Kong(香港中文大学);University of Hong Kong(香港大学);University of Washington(华盛顿大学);University of Tokyo(东京大学);Carnegie Mellon University(卡内基梅隆大学);University of California, Berkeley(加州大学伯克利分校);University of Cambridge(剑桥大学);Singapore University of Technology and Design(新加坡科技设计大学);Singapore Management University(新加坡管理学院);XGEN Labs(XGEN实验室)
Agentic Exploration of PDE Spaces using Latent Foundation Models for Parameterized Simulations
University of Michigan(密歇根大学);Universidad Politécnica de Madrid(马德里理工大学);Purdue University(普渡大学);Universitat Politècnica de València(瓦伦西亚理工大学);Caltech(加州理工学院);University of Washington(华盛顿大学)
What If Prompt Injection Never Left? Rethinking Agent Security through Cross-Session Stored Prompt Injection
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);AI Sec Lab, Beijing Chaitin Technology Co.,Ltd(北京柴坦科技有限公司AI安全实验室)
From Single Chatbots to Governed Agent Ecosystems: An Agentic AI Pattern Catalogue and Orchestration Framework for Mission-Critical Hospital Information Management Systems
Governing Execution Risk in Agentic AI Systems: A Trajectory-Guided Framework for Red Teaming
Department of Information Systems, Business Statistics and Operations Management (ISOM), Hong Kong University of Science and Technology(香港科技大学信息系统、商务统计与运营管理系(ISOM))