# textttR2AI: Towards Resistant and Resilient AI in an Evolving World

arXiv: https://arxiv.org/abs/2509.06786 · HTML: https://mlsanity.com/paper/2509.06786/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2025.

## Built on by (most cited first, 2 of 2)

- [Safety in Embodied AI: A Survey of Risks, Attacks, and Defenses](https://mlsanity.com/paper/2605.02900/) (2026)
- [ReSI: Recursive Safety Improvement toward Resistant and Resilient AI](https://mlsanity.com/paper/2610.12233/) (2026)

## Abstract (arXiv)

In this position paper, we address the persistent gap between rapidly growing AI capabilities and lagging safety progress. Existing paradigms divide into ``Make AI Safe'', which applies post-hoc alignment and guardrails but remains brittle and reactive, and ``Make Safe AI'', which emphasizes intrinsic safety but struggles to address unforeseen risks in open-ended environments. We therefore propose textitsafe-by-coevolution as a new formulation of the ``Make Safe AI'' paradigm, inspired by biological immunity, in which safety becomes a dynamic, adversarial, and ongoing learning process. To operationalize this vision, we introduce textttR2AI -- textitResistant and Resilient AI -- as a practical framework that unites resistance against known threats with resilience to unforeseen risks. textttR2AI integrates textitfast and slow safe models, adversarial simulation and verification through a textitsafety wind tunnel, and continual feedback loops that guide safety and capability to coevolve. We argue that this framework offers a scalable and proactive path to maintain continual safety in dynamic environments, addressing both near-term vulnerabilities and long-term existential risks as AI advances toward AGI and ASI.