Self-Explainability in Self-Adaptive and Self-Organising Systems: Status and Research Directions

2026-06-08

AI Summary

As AI systems grow increasingly complex, the opacity of their adaptive and self-organizing mechanisms undermines interpretability and trustworthiness, while self-explainability (SX) remains underexplored due to the absence of a systematic research framework. This study addresses this gap through a comprehensive literature review integrating qualitative analysis and conceptual modeling, offering the first unified definition, taxonomy, and hierarchical framework for SX. The analysis reveals that existing SX approaches predominantly remain at the conceptual stage, lacking practical deployment and standardized evaluation protocols. Building on these insights, the work identifies critical research gaps and establishes a foundational theoretical basis and roadmap to guide future investigations in self-explainable AI.

Abstract

The growing complexity of self-adaptive and self-organising systems, fuelled by advances in Artificial Intelligence (AI), has made them increasingly difficult to understand and trust. While Explainable AI aims to provide insight into AI decision-making, a more advanced goal is for systems to explain themselves - an ability referred to as Self-Explainability (SX). This article presents a systematic literature review on SX, analysing existing approaches, including their domains, targets, and evaluation methods. The review develops a unified definition and taxonomy of SX and introduces Levels of Self-Explainability, providing a framework for positioning current and future research. Our results show that most SX approaches remain conceptual, with few practical implementations. Moreover, there is currently no formal or de facto standard for evaluating SX, highlighting a major research gap. This work thus establishes a foundation and roadmap for advancing Self-Explainability in complex systems.

Problem

• Self-Explainability
• Self-Adaptive Systems
• Self-Organising Systems
• Explainable AI
• System Trustworthiness

Innovation

• Self-Explainability
• Self-Adaptive Systems
• Self-Organising Systems
• Explainable AI
• Systematic Literature Review