# The Black-Box Simplex Architecture for Runtime Assurance of Autonomous CPS

arXiv: https://arxiv.org/abs/2102.12981 · HTML: https://mlsanity.com/paper/2102.12981/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2021.

## Built on by (most cited first, 8 of 8)

- [Dynamic Simplex: Balancing Safety and Performance in Autonomous Cyber Physical Systems](https://mlsanity.com/paper/2302.09750/) (2023)
- [Formal Verification of Neural Certificates Done Dynamically](https://mlsanity.com/paper/2507.11987/) (2025)
- [Searching for Optimal Runtime Assurance via Reachability and Reinforcement Learning](https://mlsanity.com/paper/2310.04288/) (2023)
- [Synergistic Simplex: Cooperative Runtime Assurance for Safety-Critical Autonomous Systems](https://mlsanity.com/paper/2605.08190/) (2026)
- [Engineering Trustworthy Agentic AI for Critical Systems](https://mlsanity.com/paper/2607.18548/) (2026)
- [ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories](https://mlsanity.com/paper/2608.03866/) (2026)
- [Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive Systems](https://mlsanity.com/paper/2608.26306/) (2026)
- [Mimir: Physics-Grounded LLM Agents for Long-Horizon Irrigation Control](https://mlsanity.com/paper/2610.02038/) (2026)

## Abstract (arXiv)

The Simplex Architecture is a runtime assurance framework where control authority may switch from an unverified and potentially unsafe advanced controller to a backup baseline controller in order to maintain the safety of an autonomous cyber-physical system. In this work, we show that runtime checks can replace the requirement to statically verify safety of the baseline controller. This is important as there are many powerful control techniques, such as model-predictive control and neural network controllers, that work well in practice but are difficult to statically verify. Since the method does not use internal information about the advanced or baseline controller, we call the approach the Black-Box Simplex Architecture. We prove the architecture is safe and present two case studies where (i) model-predictive control provides safe multi-robot coordination, and (ii) neural networks provably prevent collisions in groups of F-16 aircraft, despite the controllers occasionally outputting unsafe commands.