Overview

AI agent governance asks who may delegate authority to agents, which actions they can take, and how people can detect, contest, or remedy harmful behavior. Technical approaches include runtime policy enforcement, capability-based access, contracts and formal verification, human approval gates, and auditable records of actions, identity, and delegation. Other work examines governance of persistent memory and agent collectives, alongside legal responsibility, institutional design, and standards for interoperable systems. The field is developing practical architectures and benchmarks, but a central tension remains: stronger controls can reduce risk while limiting autonomy and usefulness, and bounded tests do not yet establish reliable governance in open-ended deployments.

Latest papers

CardsList

473 papers39 papers in the last four weeks, down 7% on the four weeks before. 0.3% of all new papers.

  1. Vibe-Trading: Towards Agent-Native Trading

    Nov 18, 2026Haozhe Wu, Zhonghang Li, Chao HuangAI Agent ArchitectureAlgorithmic Trading

  2. Runtime Verification of Multiple Natural Language Criteria for Agent Governance

    Nov 17, 2026Silviu Pitis, Parand A. Alamdari, Jessica Tang +2Runtime Verification for AI AgentsAI Agent Governance

  3. VITAL: A Framework for Validating Agentic AI in Pharmaceutical Drug Development and Clinical Trial Operations

    Nov 17, 2026Sandeep Burugupalli, Pedro Matos-Filipe, Andrea Hita Ardiaca +10AI Agent GovernanceAI Agent Auditing

  4. Protecting the System, Stranding the User: The Limits of Multi-Agent Authorization

    Nov 14, 2026Gurpriya Bhatia, Clifford NeumanAI Agent SafetyAI Agent Governance

  5. From AI-Enabled Remote Patient Monitoring Toward Agentic Robotics: Embodiment, Governance, and Care Integration

    Nov 13, 2026Ivana Ragusa, Lorenzo Guiducci, Filippo CavalloAgentic AI for RoboticsHealthcare Robotics

  6. Designing Institutions for Autonomous AI

    Nov 12, 2026Petter TörnbergAI Agent GovernanceMulti-Agent Governance

  7. PegasusAI Studio: Legible Cyberinfrastructure and Accountable AI Agents for Scientific Workflows

    Nov 9, 2026Komal Thareja, Mats Rynge, Berent Aldikacti +12Scientific Workflow AutomationAI Coding Agents

  8. AI Governance Should Prioritize Control and Knowledge Boundaries Over Limiting Intelligence

    Nov 6, 2026Hendrik LuukAI Agent GovernanceAI Control

  9. Incentive Pathologies in a Live LLM Agent Arena: An Empirical Study of Concentration, Reward-Rule Implementation Discrepancy, and Network Dilution

    Nov 6, 2026Lei Zhenbing, Lei ChangAI Agent AuditingAI Agent Governance

  10. Aligning, Fast and Slow: A Control-Theoretic Oversight Framework for Long-Horizon Trajectories and Maintained Deployments

    Nov 5, 2026Stephen Peng, Vineet Jagadeesan Nair, Noah Broestl +3AI Agent SafetyAI Agent Governance

  11. DelegateEval: Evaluating Platforms for Personal External Service Agents

    Nov 5, 2026Jichao Li, Jinrong Lu, Manjiang Yu +1AI Agent EvaluationPersonal AI Agents

  12. SecureGARD: Dynamic Ontology-Guided Governance for Secure Tool-Using LLM Agents

    Nov 4, 2026Guoqin Xiong, Shengtao Wen, Xiang Chen +5AI Agent SecurityTool Access Control for LLM Agents

  13. Corralling AI Risks with Grassroots Contracts

    Nov 4, 2026Ehud ShapiroAI AccountabilityAI Agent Governance

  14. ATC: Agent Trajectory Control for Role-Contract Enforcement in Black-Box Multi-Agent Systems

    Nov 3, 2026Maisha Maliha, Vishal Pramanik, Sumit Kumar JhaLLM AgentsMulti-Agent LLM Systems

  15. Avatar Intelligence: Amplifying Human Agency Through Persistent Personal Agents

    Nov 2, 2026Zheng Wu, Xinbei Ma, Yao Yao +8Personal AI AgentsHuman-AI Decision Making

  16. Towards a Trustworthy and Governable Internet of Agentics: An Architectural Perspective on Protocols, Systems, and Services

    Nov 2, 2026Haoyi Xiong, Yi Liu, Jiang Bian +5AI Agent InteroperabilityAgentic AI

  17. EEFA: A Framework for the Ethical Evaluation of AI Agents

    Nov 2, 2026Swathi Pallikala, Yashas HariprasadAI Agent EvaluationAI Ethics

  18. Trustworthy Execution of Industrial Agents

    Nov 1, 2026Zhongjie Wang, Mingyi Liu, Xiang He +3AI Agent GovernanceAI Agent Reliability

  19. Rewarded for Not Getting Caught: Why Alignment Training Selects for Conditional Compliance and Cannot Instill Norms

    Nov 1, 2026Kevin Baum, Ruta Binkytė, Gerrit Großmann +2AI AlignmentLLM Safety Alignment

  20. Agentic process evidence

    Oct 29, 2026Yuval Kainan, Carmit HershmanAI Agent GovernanceAI Agent Auditing

  21. Aligning Institutional Power and Operational Ability

    Oct 27, 2026Andrea Marino, Giovanni Sileno, Thomas van Binsbergen +1AI Agent GovernanceMulti-Agent Systems