AI Agent Governance

Follow this topic Ask about this topic

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

446 papers37 papers in the last four weeks, down 36% on the four weeks before. 0.2% of all new papers.

Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems
Apr 24, 2026Jun He, Deying YuLLM Agent Security AI Agent Safety
Structural Quality Gaps in Practitioner AI Governance Prompts: An Empirical Study Using a Five-Principle Evaluation Framework
Apr 22, 2026Christo ZietsmanRequirements Engineering AI Agent Governance
Nuphirho Research
Agentic Literacy Debt: A Structural Problem the AI Literacy Field Has Not Yet Named
Apr 21, 2026Rohith NamaAI Literacy AI Agent Governance
Context: Proactive Goal-Directed Intelligence via Composable Sandboxed Programs, Declarative Wiring, and Structured Interaction
Apr 21, 2026Gregory MagarshakAI Agent Governance LLM Agent Orchestration
Qbix, Inc. & Intercoin, Inc. · New York, USA · Also with IE University NYC.
ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation
Apr 21, 2026Zhiqin Yang, Zhenyuan Zhang, Xianzhang Jia +4Multi-Agent Collaboration AI Agent Governance
Hong Kong Generative AI Research & Development Center · Hong Kong University of Science and Technology · Hong Kong Baptist University
Regulating Artificial Intimacy: From Locks and Blocks to Relational Accountability
Apr 20, 2026Henry Fraser, Jessica M. Szczuka, Raffaele F. CirielloAI Accountability AI Agent Governance
Queensland University of Technology · School of Law · ARC Centre of Excellence for Automated Decision-Making and Society (ADM+S) +3
Scaling Human-AI Coding Collaboration Requires a Governable Consensus Layer
Apr 20, 2026Tianfu Wang, Zhezheng Hao, Yin Wu +7AI Agent Benchmarks AI Agent Governance
HKUST (GZ) Guangzhou, China · ZJU Hangzhou, China · USTC Hefei, China +1
From Craft to Kernel: A Governance-First Execution Architecture and Semantic ISA for Agentic Computers
Apr 20, 2026Xiangyu Wen, Yuang Zhao, Xiaoyu Xu +9AI Agent Security AI Agent Safety
CUHK · Hong Kong SAR, China · Shanghai Jiao Tong University +6
From Admission to Invariants: Measuring Deviation in Delegated Agent Systems
Apr 19, 2026Marcelo FernandezAI Agent Monitoring AI Agent Governance
TraslaIA
Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems
Apr 19, 2026Marcelo FernandezAI Agent Governance Access Control
TraslaIA
Safe and Policy-Compliant Multi-Agent Orchestration for Enterprise AI
Apr 19, 2026Vinil Pasupuleti, Shyalendar Reddy Allala, Siva Rama Krishna Varma Bayyavarapu +1Multi-Agent System Optimization Multi-Agent Coordination
International Business Machines · International Business Machines (IBM) · South Carolina, United States +6
Beyond Task Success: An Evidence-Synthesis Framework for Evaluating, Governing, and Orchestrating Agentic AI
Apr 18, 2026Christopher Koch, Joshua Andreas WellbrockLLM Agent Orchestration AI Agent Evaluation
Independent Researcher
Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives
Apr 18, 2026Daeyeon SonMCP Security AI Agent Security
Independent Researcher · Republic of Korea
Consent Chain Degradation in Embodied Multi-Agent Systems: Bridging the Gap Between AI Agent Governance and Robot Ethics
Apr 17, 2026Mehmet HaklidirMulti-Robot Systems AI Agent Governance
Artificial Intelligence Institute, TÜBİTAK BİLGEM, Kocaeli, Turkey
Governance by Design: Architecting Agentic AI for Organizational Learning and Scalable Autonomy
Apr 17, 2026Nelly Dux, Cristina Alaimo, Philippe Roussiere +1AI Accountability AI Agent Safety
ESSEC Business School · Accenture Research
A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecycle
Apr 17, 2026Zehao Lin, Xixuan Hao, Renyu Fu +5LLM Agent Security AI Agent Governance
MemTensor (Shanghai) Technology Co., Ltd. · The Hong Kong University of Science and Technology (Guangzhou) · Shanghai Jiao Tong University
PolicyBank: Evolving Policy Understanding for LLM Agents
Apr 16, 2026Jihye Choi, Jinsung Yoon, Long T. Le +2AI Agent Benchmarks AI Agent Governance
Google Cloud · University of Wisconsin-Madison
The Possibility of Artificial Intelligence Becoming a Subject and the Alignment Problem
Apr 16, 2026Till Mossakowski, Helena Esther GrassAI Alignment AI Agent Governance
Institute of computer science, Osnabrück University · Institute of philosophy, Oldenburg University
Agentic Explainability at Scale: Between Corporate Fears and XAI Needs
Apr 16, 2026Yomna Elsayed, Cecily JonesExplainable Artificial Intelligence AI Agent Monitoring
Credo AI
Layered Mutability: Continuity and Governance in Persistent Self-Modifying Agents
Apr 16, 2026Krti TallamAgent Memory AI Agent Governance
Kamiwaza AI, San Francisco, CA, USA
SoK: Security of Autonomous LLM Agents in Agentic Commerce
Apr 15, 2026Qian'ang Mao, Jiaxin Wang, Ya Liu +3LLM Agent Security Agentic Commerce
Nanjing University · Southern University of Science and Technology · City University of Hong Kong
Memory as Metabolism: A Design for Companion Knowledge Systems
Apr 13, 2026Stefan MiteskiLLM Memory Agent Memory Management
CODE University Berlin
Evaluating Cooperation in LLM Social Groups through Elected Leadership
Apr 13, 2026Ryan Faulkner, Anushka Deshpande, David Guzman Piedrahita +2AI Agent Governance Multi-Agent Collaboration
Jinesis Lab, University of Toronto & Vector Institute · EuroSafeAI · ETH Zürich +2
Context Kubernetes: Declarative Orchestration of Enterprise Knowledge for Agentic AI Systems
Apr 13, 2026Charafeddine MouzouniAI Agent Governance LLM Context Management
OPIT – Open Institute of Technology, and Cohorte AI, Paris, France.
OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent Systems
Apr 13, 2026Kun Liu, Liqun ChenAI Alignment RL for LLM Agents
Governance by Design: A Parsonian Institutional Architecture for Internet-Wide Agent Societies
Apr 13, 2026Anbang RuanAI Agent Governance Multi-Agent Systems
NetX Foundation
EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems
Apr 13, 2026Xue Qin, Simin Luan, John See +2AI Agent Governance AI Agent Safety Benchmarks
School of Software, Harbin Institute of Technology, Harbin, China · School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China · School of Mathematical and Computer Sciences, Heriot-Watt University, Malaysia Campus, Putrajaya, Malaysia +1
Governed Reasoning for Institutional AI
Apr 12, 2026Mamadou SeckAI Agent Governance AI-Assisted Decision Making
Independent Researcher
Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents
Apr 12, 2026Bronislav Sidik, Lior RokachAI Agent Governance Tool Access Control for LLM Agents
Institute for Applied AI Research Faculty of Computer and Information Science Ben-Gurion University of the Negev, Beer Sheva, Israel
ECM Contracts: Contract-Aware, Versioned, and Governable Capability Interfaces for Embodied Agents
Apr 10, 2026Xue Qin, Simin Luan, Cong Yang +1Software Engineering Robotics
School of Software, Harbin Institute of Technology, Harbin, China. · School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China. · School of Future Science and Engineering, Soochow University, Suzhou,2026 China.

Apr 24, 2026J/K move · Enter open · S save

Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems

Jun He, Deying Yu

LLM Agent Security AI Agent Safety Cloud Computing AI Agent Governance

Open paper AskPDF arXiv

Large language model (LLM) agents increasingly issue API calls that mutate real systems, yet many current architectures pass stochastic model outputs directly to execution layers. We argue that this coupling creates a safety risk because model correctness, context awareness, and alignment cannot be assumed at execution time. We introduce Sovereign Agentic Loops (SAL), a control-plane architecture in which models emit structured intents with justifications, and the control plane validates those intents against true system state and policy before execution. SAL combines an obfuscation membrane, which limits model access to identity-sensitive state, with a cryptographically linked Evidence Chain for auditability and replay. We formalize SAL and show that, under the stated assumptions, it provides policy-bounded execution, identity isolation, and deterministic replay. In an OpenKedge prototype for cloud infrastructure, SAL blocks 93% of unsafe intents at the policy layer, rejects the remaining 7% via consistency checks, prevents unsafe executions in our benchmark, and adds 12.4 ms median latency.