conference paper published yes Zhengqi Yu author 20aa2ae8-f2f1-11ed-bbfa-8205053f1342 Dorde Zikelic author 294AA7A6-F248-11E8-B48F-1D18A9856A870000-0002-4681-1699 Thomas A Henzinger author 40876CD8-F248-11E8-B48F-1D18A9856A870000-0002-2985-7724 ToHe department AAAI: Conference on Artificial Intelligence Vigilant Algorithmic Monitoring of Software project Learning-based methods provide a promising approach to solving highly non-linear control tasks that are often challenging for classical control methods. To ensure the satisfaction of a safety property, learning-based methods jointly learn a control policy together with a certificate function for the property. Popular examples include barrier functions for safety and Lyapunov functions for asymptotic stability. While there has been significant progress on learning-based control with certificate functions in the white-box setting, where the correctness of the certificate function can be formally verified, there has been little work on ensuring their reliability in the black-box setting where the system dynamics are unknown. In this work, we consider the problems of certifying and repairing neural network control policies and certificate functions in the black-box setting. We propose a novel framework that utilizes runtime monitoring to detect system behaviors that violate the property of interest under some initially trained neural network policy and certificate. These violating behaviors are used to extract new training data, that is used to re-train the neural network policy and the certificate function and to ultimately repair them. We demonstrate the effectiveness of our approach empirically by using it to repair and to boost the safety rate of neural network policies learned by a state-of-the-art method for learning-based control on two autonomous system control tasks. Association for the Advancement of Artificial Intelligence2025Philadelphia, PA, United States eng 2159-5399 2374-3468 2412.1299610.1609/aaai.v39i25.34840 392526409-26417 Yu, E., Zikelic, D., &#38; Henzinger, T. A. (2025). Neural control and certificate repair via runtime monitoring. In <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i> (Vol. 39, pp. 26409–26417). Philadelphia, PA, United States: Association for the Advancement of Artificial Intelligence. <a href="https://doi.org/10.1609/aaai.v39i25.34840">https://doi.org/10.1609/aaai.v39i25.34840</a> E. Yu, D. Zikelic, T.A. Henzinger, in:, Proceedings of the 39th AAAI Conference on Artificial Intelligence, Association for the Advancement of Artificial Intelligence, 2025, pp. 26409–26417. E. Yu, D. Zikelic, and T. A. Henzinger, “Neural control and certificate repair via runtime monitoring,” in <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i>, Philadelphia, PA, United States, 2025, vol. 39, no. 25, pp. 26409–26417. Yu, Emily, et al. “Neural Control and Certificate Repair via Runtime Monitoring.” <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i>, vol. 39, no. 25, Association for the Advancement of Artificial Intelligence, 2025, pp. 26409–17, doi:<a href="https://doi.org/10.1609/aaai.v39i25.34840">10.1609/aaai.v39i25.34840</a>. Yu E, Zikelic D, Henzinger TA. 2025. Neural control and certificate repair via runtime monitoring. Proceedings of the 39th AAAI Conference on Artificial Intelligence. AAAI: Conference on Artificial Intelligence vol. 39, 26409–26417. Yu E, Zikelic D, Henzinger TA. Neural control and certificate repair via runtime monitoring. In: <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i>. Vol 39. Association for the Advancement of Artificial Intelligence; 2025:26409-26417. doi:<a href="https://doi.org/10.1609/aaai.v39i25.34840">10.1609/aaai.v39i25.34840</a> Yu, Emily, Dorde Zikelic, and Thomas A Henzinger. “Neural Control and Certificate Repair via Runtime Monitoring.” In <i>Proceedings of the 39th AAAI Conference on Artificial Intelligence</i>, 39:26409–17. Association for the Advancement of Artificial Intelligence, 2025. <a href="https://doi.org/10.1609/aaai.v39i25.34840">https://doi.org/10.1609/aaai.v39i25.34840</a>. 196682025-05-11T22:02:40Z2025-05-12T09:49:25Z