Overview

Runtime assurance studies how to check and, when needed, modify or block a system’s actions while it is running, especially when a learned component cannot be trusted to behave safely in every situation. Common approaches include Simplex architectures with verified backup controllers, control-barrier-function and rule-based shields, and monitors that use contracts, reachability, or statistical risk bounds to trigger recovery or abstention. These methods are tested in settings such as robot manipulation, autonomous driving, spacecraft control, power grids, and tool-using agents, where they must balance safety with task success, latency, and operator control. A central challenge is making guarantees hold under partial observation, disturbances, and changing conditions without making interventions so conservative that the system becomes ineffective; many results still depend on stated assumptions or bounded evaluations.

Latest papers

CardsList

71 papers8 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

  1. ROSMonitoring in Action: Runtime Monitoring and Enforcement for ROS 2 Actions

    Nov 17, 2026Giacomo Paltrinieri, Angelo FerrandoRuntime Assurance

  2. Certify, Then Select: Viability-Aware Runtime Steering of Frozen Diffusion Policies

    Nov 14, 2026Angelo Moroncelli, Loris RovedaRobotic ControlRuntime Assurance

  3. Runtime Safety and Emergency Stops on a Full-Size Humanoid: Deployment Lessons and a Case for Graduated Force Authority

    Nov 11, 2026Max Conway, Yutong Zhang, Allen Devaraj +3Robot SafetyHumanoid Robotics

  4. XAI-Driven Confidence Estimation for OOD-Resilient Runtime Prediction

    Nov 9, 2026Mahmoud Sanad, Mohammed Bakr Sikal, Osama Abboud +2Confidence EstimationDistribution Shift Robustness

  5. 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

  6. CoSafe: Cooperative Runtime Safety Assurance for Mixed-Traffic Autonomous Driving

    Nov 4, 2026Dingji Wang, You Lu, Haowen Jiang +5Runtime AssuranceIntelligent Transportation Systems

  7. Assuring Learning-Enabled Cyber-Physical Systems with Foundation Models: A Neuro-Symbolic Agenda for Testing, Verification, and Runtime Assurance

    Oct 29, 2026Xi Zheng, Ivan Ruchkin, Hong Jin Kang +11Cyber-Physical SystemsRuntime Assurance

  8. Context-dependent Runtime Construction of Safe Regions of Attraction from Design-Time Identification for Multi-Candidate Simplex Architectures

    Oct 26, 2026Georg Jäger, Nils-Jonathan Friedrich, Norman Seyffer +2Safety-Critical ControlRuntime Assurance

  9. AutoAgent0: An Agentic Runtime for Safe Closed-Loop Driving

    Oct 13, 2026Jiageng Liu, Seth Z. Zhao, Zewei Zhou +9Autonomous Driving PlanningRuntime Assurance

  10. Mission-Aware Attestation Envelopes for Time-Critical Autonomous Action: A Hardware-in-the-Loop V2I Study

    Oct 6, 2026Dimitrios Nikou, Nikolaos Kekatos, Sophia Petridou +1Remote AttestationRuntime Assurance

  11. SoK: Semantic Decision Engines in Network Control Loops

    Oct 5, 2026Delong Li, Chen Li, Xu Wang +3Safety-Critical ControlRuntime Assurance

  12. Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents

    Sep 30, 2026Serhii ZabolotniiAI Agent SafetyRuntime Enforcement for AI Agents

  13. Taming the Agentic RAN: Stability-Guaranteed Arbitration of Autonomous AI Agents in O-RAN

    Sep 16, 2026Seyed Bagher Hashemi Natanzi, Bo TangMulti-Agent ControlOpen Radio Access Network

  14. RobResilience: Implementing and Evaluating a Resilience Framework for Cyber-Physical Embodied Systems

    Sep 15, 2026Gysella Imrell, Emanuele Miotto, Mahya Mohammadi Kashani +2Cyber-Physical SystemsAutonomous Cyber Defense

  15. Generator-Independent Runtime Assurance under Partial Observation

    Sep 5, 2026Guangxi Wan, Yongbo Xie, Yuqi Liu +4Runtime AssuranceRuntime Verification

  16. Rethinking World Models for Safety-Critical Embodied Systems

    Sep 3, 2026Kailang Ma, Heye Huang, Inhi Kim +1Runtime AssuranceEmbodied World Models

  17. CURA: Certified Runtime Alarms for Computer-Use Agents

    Aug 28, 2026Divake Kumar, Sina Tayebati, Devashri Naik +5AI Agent MonitoringComputer-Use Agents

  18. Herding End-to-End Autonomous Driving via Neuro-Symbolic Safety Guards

    Aug 11, 2026Simón Patiño Idarraga, Erick Silva, Rehana Yasmin +1End-to-End Autonomous DrivingAutonomous Driving Safety Evaluation

  19. Dual Stress: Runtime Safety Monitoring for Safety-Constrained MPC Navigation

    Aug 11, 2026Jamil Chahine, Wenqi Cai, John Abanes +1Safety-Critical ControlModel Predictive Control

  20. SkillSentry: Reliable Skill Execution for LLM Agents via Runtime Assurance

    Aug 10, 2026You Lu, Xinyu Huang, Bihuan Chen +1LLM Agent Skill LearningLLM Agents

  21. EduPluginBench: Executable Assurance for AI-Generated Educational Plugins

    Aug 1, 2026Nizam KadirSoftware SecurityRuntime Assurance