Preparing for Super-Reactivity: Early Fault-Detection in the Development of Exceedingly Complex Reactive Systems

TL;DR

The paper proposes an AI-enabled architecture for early fault detection in complex, evolving reactive systems, leveraging large language models for simulation and analysis to enhance safety and reliability.

Contribution

It introduces a novel architecture utilizing AI tools and natural language processing for early fault detection in super-reactive systems, addressing complexity and interaction challenges.

Findings

Effective early fault detection enabled by AI-based simulation.

Improved understanding of interdependencies among requirements.

Enhanced safety and reliability in complex reactive systems.

Abstract

We introduce the term Super-Reactive Systems to refer to reactive systems whose construction and behavior are complex, constantly changing and evolving, and heavily interwoven with other systems and the physical world. Finding hidden faults in such systems early in planning and development is critical for human safety, the environment, society and the economy. However, the complexity of the system and its interactions and the absence of adequate technical details pose a great obstacle. We propose an architecture for models and tools to overcome such barriers and enable simulation, systematic analysis, and fault detection and handling, early in the development of super-reactive systems. The approach is facilitated by the inference and abstraction capabilities and the power and knowledge afforded by large language models and associated AI tools. It is based on: (i) deferred, just-in-time interpretation of model elements that are stored in natural language form, and (ii) early capture of tacit interdependencies among seemingly orthogonal requirements.