Agentic, Autonomous and Explainable AI in Smart Agriculture: A Systematic Literature Review
TL;DR
The evidence reveals an explainability-autonomy divide and substantial field-validation and reproducibility gaps in agentic/autonomous AI and/or XAI in agricultural systems using sensor, robotic or computer-vision data and reporting an evaluation.
Abstract
Agentic, autonomous and explainable AI (XAI) is growing in smart agriculture, but its design, evaluation and integration have not been systematically mapped. Following PRISMA 2020, we searched Web of Science Core Collection, Scopus and IEEE Xplore through 14 June 2026 for English-language peer-reviewed articles and conference papers (2016–2026) implementing agentic/autonomous AI and/or XAI in agricultural systems using sensor, robotic or computer-vision data and reporting an evaluation. Two reviewers independently screened, extracted data and appraised methodological quality using a six-item CASP-style rubric. Results were synthesised descriptively using counts, percentages, cross-tabulations and thematic mapping; meta-analysis was inappropriate because tasks, datasets and metrics were heterogeneous. Of 2255 records, 322 studies were included. XAI dominated (69.6%), whereas autonomous (14.0%) and agentic (12.1%) designs were less common; only 4.3% combined autonomy with explainability. Disease detection was the leading application (33.5%). Most systems remained at the perception/decision-support level (78.9%); 17.4% were field-validated and 4.3% validated explanations agronomically. The evidence reveals an explainability-autonomy divide and substantial field-validation and reproducibility gaps. Explainable-by-design agentic systems require agronomic validation and shared evaluation standards. The review received no external grant funding and was not registered.
