Self-Explainability in Self-Adaptive and Self-Organising Systems: Status and Research Directions
arXiv:2606.09568v1 Announce Type: new 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 definit
The increasing complexity of AI systems, especially in self-adaptive and self-organizing contexts, necessitates greater explainability to build trust and facilitate further development.
Self-explainability is a critical next step for AI adoption in high-stakes environments, directly addressing transparency and reliability concerns that hinder widespread deployment.
The focus is shifting from external explainability (XAI) to internal, autonomous explainability (SX), enabling systems to articulate their own decisions and operational states.
- · AI developers
- · High-reliability industries
- · AI ethics research
- · AI auditing firms
- · Black-box AI systems
- · Traditional XAI approaches that are not integrated into system design
Increased trust in AI systems due to their ability to justify actions.
Faster and safer deployment of autonomous AI in critical infrastructure and decision-making.
The emergence of AI systems capable of recursively explaining their own self-explanation mechanisms, potentially leading to more advanced forms of artificial general intelligence (AGI).
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI