Skip to main content
SAICA-KG

Taxonomies

Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes

Shah et al. (arXiv:2603.06847) · v2026-03 · first published 2026-03-06

Scope

Grounded-theory taxonomy of faults in agentic AI systems, derived from 13,602 issues and PRs across 40 open-source agentic-AI repositories, with stratified sampling to 385 faults and developer-study validation (n=145). Three parallel taxonomies: fault types (5 dimensions, 13 major categories, 37 fault subcategories); 13 symptom classes; 12 root-cause categories. This is the empirical corpus SAICA-KG uses for its v0.1 back-test.

Source →License: arXiv preprint; CC-BYPaper →

Why it's ingested

Shah et al. 2026 is the single most comprehensive empirical fault characterization for agentic AI to date, with a 385-fault grounded-theory sample across 40 real repos — exactly the scale SAICA-KG needs to argue its FailureMode partition is honest-MECE. Intended crosswalks: SHAH-MAJ-10 (Dependency Management) -> obsolescence + supply_chain_attack; SHAH-MAJ-03 (Tool Execution/API Usage) -> logic_error + fabrication (API); SHAH-MAJ-08 (Context/State Persistence) -> context_pollution; SHAH-MAJ-09 (Input Interpretation/Logic) -> logic_error; SHAH-RC-04 (Auth/Credential) -> security_vulnerability; SHAH-RC-08 (API Schema Drift) -> obsolescence. Coverage ratio against SAICA-KG's FailureMode enum is the v0.1 honest-MECE evidence.

Categories & crosswalks

Each row lists one external category and any SAICA-KG FailureModes that cross-walk into it.

Notes

Top-level structure (5 dimensions, 13 major categories, 12 root causes) is canonical per the arXiv v1 HTML; the 37 fault subcategories are enumerated in the paper and will be expanded into full category rows as a v0.2 task. Symptom-class and full subcategory labels are pending full-text verification. This taxonomy is the empirical back-test corpus: SAICA-KG's FailureMode axis will be evaluated against whether SHAH-* faults map cleanly into its eight-class FailureMode enum.

View raw YAML on GitHub →