Runtime Enforcement for AI Agents

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

312 papers50 papers in the last four weeks, down 51% on the four weeks before. 0.4% of all new papers.

  1. Intent Contracts: Taking Tools Away from Agents

    Nov 18, 2026Ziyuan Wang, Genliang Zhu, Xiaobo Chen +1Tool Access Control for LLM AgentsLLM Agent Safety

  2. Invariant-Aware Harness Enforcement to Protect LLM Agents from Silent API Failures

    Nov 16, 2026Sajib Acharjee Dip, Brian Ouyang, Lala MotlhabiRuntime Enforcement for AI AgentsLLM Agent Harnesses

  3. Agent-ZTA: A chain-Aware Zero Trust Model for Bidirectional Security-State Propagation and Runtime Containment in Multi-Agent Delegation

    Nov 13, 2026Asadullah Abdullah Khan, Toqeer Ali SyedMulti-Agent System SecurityRuntime Enforcement for AI Agents

  4. Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents

    Nov 13, 2026Mike He, Ankush Desai, Sharad Malik +1LLM Agent SafetyLLM Agent Planning

  5. Learn then Bet: Learning Interpretable Rules for Reliable Agent Intervention

    Nov 13, 2026You-Lin Chen, Xinyi Lisa Chen, Pedro Herrero-Vidal +3AI Agent MonitoringRuntime Enforcement for AI Agents

  6. guardscope: Measuring Which Actions Runtime Controls Check in LLM Agent Systems

    Nov 11, 2026Kentaroh Toyoda, Alex Leung, Bhuvaneswari URuntime Enforcement for AI AgentsAI Agent Auditing

  7. EvoX: Rethinking the Agent Harness as a Runtime Policy

    Nov 11, 2026Haoyang Zhang, Qumeng Sun, Xiao Zhang +3LLM Agent HarnessesRuntime Enforcement for AI Agents

  8. Mach2: Scientific Discovery Platform with Deterministic Execution Constraints

    Nov 10, 2026Vansh Sharma, Venkat RamanLLM Agent OrchestrationRuntime Enforcement for AI Agents

  9. LEASH: Stay Safe in Agentic Robotics

    Nov 10, 2026Qinfeng Zhu, Weiguang Zhao, Ke Sun +5Robot SafetyAgentic AI for Robotics

  10. From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses

    Nov 10, 2026Simon Hegelich, Bardh Prenkaj, Habiba Sarhan +5AI Agent SecurityTool Access Control for LLM Agents

  11. When Routine Operations Break Architectural Pattern Relationships in LLM Agent Harnesses

    Nov 6, 2026Boming Xia, Qinghua Lu, Dino Sejdinovic +1LLM Agent HarnessesSoftware Engineering

  12. zkARc: Succinctly Verifiable Proofs for Neurosymbolic Natural Language Formalization and Verification

    Nov 5, 2026Wyatt Benno, Alberto Centelles, Aman Goel +1Formal VerificationRuntime Enforcement for AI Agents

  13. Trust Responsive Runtime Authorization for Agentic AI with Empirical Characterization of Policy Behavior and Parameter Sensitivity

    Nov 4, 2026Ahsan Habib Shihab, Imre Felde, Ramis Akhmedov +4Runtime Enforcement for AI AgentsAccess Control

  14. Signed, Sealed, Leaked: Trust Beyond Signature for MCP Toolchains

    Nov 4, 2026Yichiet Aun, Mohammed A. Alhartomi, Jing Jie Tan +4AI Agent SecurityMCP Security

  15. RuntimeTickets: Source-Grounded Security Obligations for Agent Skills

    Nov 2, 2026Kuiyi Gao, Xue Liu, Bowei HeLLM Agent SecurityRuntime Enforcement for AI Agents

  16. LEANGUARD: Lean-Verified Guardrails for Tool-Using Agents

    Nov 2, 2026Sreehari Sankar, Debargha Ganguly, Vikash Singh +17Tool Access Control for LLM AgentsLLM Guardrails

  17. Trustworthy Execution of Industrial Agents

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

  18. Dependable Agents Need Hard and Fuzzy Rules

    Oct 31, 2026Frederick RothLLM GuardrailsRuntime Enforcement for AI Agents