@article{4840,
  author = {Areeya Khuha},
  title = {A Hierarchical Failure Taxonomy for Reliability Assessment of AI Agents: An Empirical Analysis of the Agent Failure Atlas 2026 Benchmark},
  journal = {Journal of Information Technology Review},
  year = {2026},
  volume = {17},
  number = {4},
  doi = {https://doi.org/10.6025/jitr/2026/17/4/204-226},
  url = {https://www.dline.info/jitr/fulltext/v17n4/jitrv17n4_2.pdf},
  abstract = {As large language model (LLM) based applications evolve into autonomous, action oriented AI agents, their
evaluation can no longer rely on binary success/failure metrics. Agentic systems operate through dynamic,
multi-step interactions with tools and environments, introducing complex failure modes that propagate and
cascade. This study presents a hierarchical failure taxonomy and an empirical reliability assessment using
the Agent Failure Atlas 2026 benchmark. Analyzing 3,336 agent runs encompassing 43,477 trajectory steps
and 3,802 failure events, we characterize agent reliability across four dimensions: frequency, criticality,
cascading behavior, and recoverability. Our results reveal a two dimensional reliability landscape: high
prevalence but largely recoverable failures (e.g., tool use and state tracking errors) contrast sharply with
low prevalence but highly critical failures (e.g., validation and output errors). Furthermore, we show that
intermediate failures often resolve through agent self correction, decoupling run level error rates from final
task success. By shifting the analytical focus from isolated outcome accuracy to mechanistic failure
propagation, this framework provides a foundational methodology for reliability engineering, risk mitigation,
and the safe deployment of autonomous AI systems.},
}