[2601.20666] Learning Contextual Runtime Monitors for Safe AI-Based Autonomy

Computer Science > Machine Learning arXiv:2601.20666 (cs) [Submitted on 28 Jan 2026 (v1), last revised 2 Mar 2026 (this version, v2)] Title:Learning Contextual Runtime Monitors for Safe AI-Based Autonomy Authors:Alejandro Luque-Cerpa, Mengyuan Wang, Emil Carlsson, Sanjit A. Seshia, Devdatt Dubhashi, Hazem Torfah View a PDF of the paper titled Learning Contextual Runtime Monitors for Safe AI-Based Autonomy, by Alejandro Luque-Cerpa and 5 other authors View PDF Abstract:We introduce a novel framework for learning context-aware runtime monitors for AI-based control ensembles. Machine-learning (ML) controllers are increasingly deployed in (autonomous) cyber-physical systems because of their ability to solve complex decision-making tasks. However, their accuracy can degrade sharply in unfamiliar environments, creating significant safety concerns. Traditional ensemble methods aim to improve robustness by averaging or voting across multiple controllers, yet this often dilutes the specialized strengths that individual controllers exhibit in different operating contexts. We argue that, rather than blending controller outputs, a monitoring framework should identify and exploit these contextual strengths. In this paper, we reformulate the design of safe AI-based control ensembles as a contextual monitoring problem. A monitor continuously observes the system's context and selects the controller best suited to the current conditions. To achieve this, we cast monitor learning as a conte...