Explainable artificial intelligence in autonomous information technology systems: A survey of open challenges and research directions

The paradigm of Explainable Artificial Intelligence (XAI) has been developed as a solution for increasing transparency, interpretability, and accountability of Artificial Intelligence (AI) models used in autonomous Information Technology (IT) systems. The fast adoption of autonomous AI technologies in cybersecurity, digital forensics, intelligent network management, cloud orchestration, automated incident response, and other mission-critical applications has dramatically increased the need for transparent, interpretable decision-making, regulatory compliance, and human-centered AI. Despite the fact that such advanced learning algorithms as Deep Neural Networks (DNNs), reinforcement learning, and graph-based learning models have demonstrated outstanding predictability capabilities, the black-box nature of these algorithms still limits their applicability to autonomous environments due to safety concerns. This survey aims to provide a systematic review of XAI approaches to autonomous IT systems through critical synthesis of recent research conducted in the field between 2022 and 2026. The review discusses XAI approaches, application domains, evaluation criteria, features, problems associated with explainability, and research directions. As opposed to the previous surveys of Explainable AI in autonomous IT systems that usually focus on providing descriptive summaries, the proposed review offers a critical synthesis of recent findings, a comparative study of popular XAI techniques for various autonomous IT applications, and a detailed discussion of their appropriateness in terms of transparency, interpretability, computational efficiency, and explanation validity. Moreover, the survey focuses on how XAI techniques can be applied to address ethical, regulatory, security, and human-centric aspects of autonomous decision-making. In addition to this, the survey reveals gaps in existing research, unresolved challenges, and promising research directions related to XAI in autonomous IT systems.

Authors

Institutions

Publication Details

Journal
Journal of Intelligent & Fuzzy Systems
Published
2026-11-21
DOI
https://doi.org/10.1177/18758967261509028
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Explainable artificial intelligence in autonomous information technology systems: A survey of open challenges and research directions

Vikram Kulkarni, Anand Wanjari, Rajendhar Puppala, M. Ankush Kumar
Journal of Intelligent & Fuzzy Systems
Explainable Artificial Intelligence (XAI)
article

Explainable artificial intelligence in autonomous information technology systems: A survey of open challenges and research directions

Vikram Kulkarni, Anand Wanjari, Rajendhar Puppala, M. Ankush Kumar
article en

Abstract

The paradigm of Explainable Artificial Intelligence (XAI) has been developed as a solution for increasing transparency, interpretability, and accountability of Artificial Intelligence (AI) models used in autonomous Information Technology (IT) systems. The fast adoption of autonomous AI technologies in cybersecurity, digital forensics, intelligent network management, cloud orchestration, automated incident response, and other mission-critical applications has dramatically increased the need for transparent, interpretable decision-making, regulatory compliance, and human-centered AI. Despite the fact that such advanced learning algorithms as Deep Neural Networks (DNNs), reinforcement learning, and graph-based learning models have demonstrated outstanding predictability capabilities, the black-box nature of these algorithms still limits their applicability to autonomous environments due to safety concerns. This survey aims to provide a systematic review of XAI approaches to autonomous IT systems through critical synthesis of recent research conducted in the field between 2022 and 2026. The review discusses XAI approaches, application domains, evaluation criteria, features, problems associated with explainability, and research directions. As opposed to the previous surveys of Explainable AI in autonomous IT systems that usually focus on providing descriptive summaries, the proposed review offers a critical synthesis of recent findings, a comparative study of popular XAI techniques for various autonomous IT applications, and a detailed discussion of their appropriateness in terms of transparency, interpretability, computational efficiency, and explanation validity. Moreover, the survey focuses on how XAI techniques can be applied to address ethical, regulatory, security, and human-centric aspects of autonomous decision-making. In addition to this, the survey reveals gaps in existing research, unresolved challenges, and promising research directions related to XAI in autonomous IT systems.

Journal of Intelligent & Fuzzy Systems
Narsee Monjee Institute of Management Studies (IN), Columbus Technologies and Services (United States) (US), JSPM University (IN)
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon