Runtime Enforcement for AI Agents

Ask about this topic

Overview

Runtime enforcement governs what AI agents may do while they are running, especially when tool calls can change files, access data, spend money, or control devices. Common approaches intercept actions at a trusted boundary and apply permissions, policies, behavioral contracts, or formal checks; other systems track action history and provenance, require human approval, or verify effects before committing them. These controls are studied in settings such as coding and web agents, financial workflows, scientific tools, and robotics, with benchmarks measuring both blocked attacks and preserved task success. A central challenge is balancing safety with useful autonomy: policies must account for context and changing state, while evidence for guarantees often remains limited to specific environments and assumptions.

Latest papers

CardsList

279 papers81 papers in the last four weeks, up 8% on the four weeks before. 0.5% of all new papers.

  1. Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents

    Apr 5, 2026Mohammad Hossein ChinaeiAI Agent SecurityRuntime Enforcement for AI Agents

    Independent Researcher

  2. SentinelAgent: Intent-Verified Delegation Chains for Securing Federal Multi-Agent AI Systems

    Apr 3, 2026KrishnaSaiReddy PatilAI Agent GovernanceMulti-Agent System Security

  3. Type-Checked Compliance: Deterministic Guardrails for Agentic Financial Systems Using Lean 4 Theorem Proving

    Apr 1, 2026Devakh Rashie, Veda RashiLLM GuardrailsAI Regulatory Compliance

    Independent Researcher Centreville, Virginia, USA · Thomas Jefferson High School for Science and Technology Alexandria, VA, USA

  4. Empirical Validation of the Classification-Verification Dichotomy for AI Safety Gates

    Mar 31, 2026Arsenios ScrivensAI Agent SafetyAI Safety Evaluation

  5. ElephantBroker: A Knowledge-Grounded Cognitive Runtime for Trustworthy AI Agents

    Mar 26, 2026Cristian Lupascu, Alexandru LupascuLLM Agent MemoryLLM Agent Reliability

    Elephant Broker, 050141 Bucharest, Romania

  6. ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

    Mar 25, 2026Songyang Liu, Chaozhuo Li, Chenxu Wang +8AI Agent SecurityLLM Agent Security

    Beijing University of Posts and Telecommunications · Beijing Academy of Artificial Intelligence · China Academy of Information and Communications Technology

  7. AgentWall: A Runtime Safety Layer for Local AI Agents

    Mar 24, 2026Ashwin AravindAI Agent SafetyRuntime Enforcement for AI Agents

  8. Agent-Sentry: Bounding LLM Agents via Execution Provenance

    Mar 24, 2026Rohan Sequeira, Stavros Damianakis, Umar Iqbal +1Computer-Use Agent SafetyAI Agent Security

    University of Southern California, Los Angeles, California, USA · Washington University in St. Louis, St. Louis, Missouri, USA

  9. NuHF Claw: A Risk Constrained Cognitive Agent Framework for Human Centered Procedure Support in Digital Nuclear Control Rooms

    Mar 23, 2026Xingyu Xiao, Jiejuan Tong, Jun Sun +4AI Agent SafetyHuman-in-the-Loop AI

    Institute of Nuclear and New Energy Technology, Tsinghua University, Beijing, 100084, China · National Key Laboratory of Human Factors Engineering, Beijing, 100094, China · Institute of Software, Chinese Academy of Sciences, Beijing, 100045, China

  10. Session Risk Memory (SRM): Temporal Authorization for Deterministic Pre-Execution Safety Gates

    Mar 22, 2026Florin Adrian ChitanAI Agent SafetyRuntime Enforcement for AI Agents

    Independent Researcher, ILION Project

  11. Before the Tool Call: Deterministic Pre-Action Authorization for Autonomous AI Agents

    Mar 21, 2026Uchi UchibekeAI Agent SecurityTool-Use Authorization

    APort Technologies Inc., Toronto, Canada

  12. Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agents

    Mar 20, 2026Cailin Winston, Claris Winston, René JustTool Access Control for LLM AgentsLLM Agent Verification

    University of Washington Seattle, USA

  13. Agent Control Protocol: Admission Control for Agent Actions

    Mar 19, 2026Marcelo FernandezRuntime Enforcement for AI AgentsAI Agent Governance

    TraslaIA

  14. A Trace-Based Assurance Framework for Agentic AI Orchestration: Contracts, Testing, and Governance

    Mar 18, 2026Ciprian Paduraru, Petru-Liviu Bouruc, Alin StefanescuAI Agent ReliabilityLLM Agent Orchestration

    University of Bucharest Romania · University of Bucharest & Institute for Logic and Data Science Romania

  15. Runtime Governance for AI Agents: Policies on Paths

    Mar 17, 2026Maurits Kaptein, Vassilis-Javed Khan, Andriy PodstavnychyAI Agent GovernanceRuntime Enforcement for AI Agents

    Eindhoven University of Technology, Eindhoven, The Netherlands · Kyvvu B.V., Nijmegen, The Netherlands

  16. Proactive Rejection and Grounded Execution: A Dual-Stage Intent Analysis Paradigm for Safe and Efficient AIoT Smart Homes

    Mar 17, 2026Xinxin Jin, Zhengwei Ni, Zhengguo Sheng +1Language Model-Based ControlAI Agent Reliability

    School of Information and Electronic Engineering (Sussex Artificial Intelligence Institute), Zhejiang Gongshang University, Hangzhou 310018, China. · Sussex Artificial Intelligent Institute, Zhejiang Gongshang University, Hangzhou 310018, China · Department of Engineering and Design, University of Sussex, BN1 9RH, Brighton, U.K. +3

  17. Agent Lifecycle Toolkit (ALTK): Reusable Middleware Components for Robust AI Agents

    Mar 16, 2026Zidane Wright, Jason Tsay, Anupama Murthi +8AI Agent ReliabilityRuntime Enforcement for AI Agents

    IBM Research, New York, NY, USA · IBM Research, Haifa, Israel · IBM, Argentina

  18. Visual Confused Deputy: Exploiting and Defending Perception Failures in Computer-Using Agents

    Mar 16, 2026Xunzhuo Liu, Bowei He, Xue Liu +3Computer-Use Agent SafetyAI Agent Security

    vLLM Semantic Router Project · MBZUAI · McGill University +2

  19. Cryptographic Runtime Governance for Autonomous AI Systems: The Aegis Architecture for Verifiable Policy Enforcement

    Mar 15, 2026Adam Massimo MazzocchettiRuntime Enforcement for AI AgentsAI Agent Governance

    SPQR Technologies Inc.

  20. The Bureaucracy of Speed: Structural Equivalence Between Memory Consistency Models and Multi-Agent Authorization Revocation

    Mar 10, 2026Vladyslav ParakhinAccess ControlTool Access Control for LLM Agents

    Senior Data Engineer, Okta

  21. Execution Is the New Attack Surface: Survivability-Aware Agentic Crypto Trading with OpenClaw-Style Local Executors

    Mar 10, 2026Ailiya Borjigin, Igor Stadnyk, Ben Bilski +2AI Agent SafetyRuntime Enforcement for AI Agents

    True Trading

  22. Real-Time Trust Verification for Safe Agentic Actions using TrustBench

    Mar 10, 2026Tavishi Sharma, Vinayak Sharma, Pragya SharmaAI Agent SafetyAI Agent Reliability

    School of Computing and Augmented Intelligence, Arizona State University, Tempe, USA · Dept. of Electrical and Computer Engineering, University of California Los Angeles, Los Angeles, USA

  23. Tool Receipts, Not Zero-Knowledge Proofs: Practical Hallucination Detection for AI Agents

    Mar 9, 2026Abhinaba BasuHallucination DetectionLLM Agent Verification

  24. Right in Time: Reactive Reasoning in Regulated Traffic Spaces

    Mar 4, 2026Simon Kohaut, Benedict Flade, Julian Eggert +2Runtime Enforcement for AI AgentsIntelligent Transportation Systems

    Artificial Intelligence and Machine Learning Lab, Department of Computer Science, TU Darmstadt, 64283 Darmstadt, Germany · Konrad Zuse School of Excellence in Learning and Intelligent Systems · Honda Research Institute Europe GmbH, Carl-Legien-Str. 30, 63073 Offenbach, Germany +4

  25. AI Space Physics: Constitutive boundary semantics for open AI institutions

    Mar 3, 2026Oleg Romanchuk, Roman BondarAI Agent GovernanceAI Governance

  26. ContextCov: Deriving and Enforcing Executable Constraints from Agent Instruction Files

    Feb 28, 2026Reshabh K SharmaRuntime Enforcement for AI AgentsCoding Agents

    University of Washington Seattle, Washington, USA

  27. AI Runtime Infrastructure

    Feb 28, 2026Christopher CruzRuntime Enforcement for AI AgentsLLM Agent Workflow Optimization

  28. Atomicity for Agents: Exposing, Exploiting, and Mitigating TOCTOU Vulnerabilities in Browser-Use Agents

    Feb 28, 2026Linxi Jiang, Zhijie Liu, Haotian Luo +1AI Agent SecurityWeb Agents

    The Ohio State University

  29. AESP: A Human-Sovereign Economic Protocol for AI Agents with Privacy-Preserving Settlement

    Feb 27, 2026Jian Sheng WangAI Agent GovernanceHuman Oversight of AI

    Yeah LLC

  30. The Auton Agentic AI Framework

    Feb 27, 2026Sheng Cao, Zhao Chang, Chang Li +3Agentic AILLM Agent Orchestration