Taxonomy
AI Agent Failure Taxonomy
These are two independent axes over the same incidents, not one flat list of categories. All 122 incidents are classified by what broke — 8 of them as systemic findings, counted at the foot of this page rather than among the failure modes. 122 carry a root cause and are classified below.
What broke
The observable failure. Excludes systemic findings, which are counted separately below.
- Destructive Action56
- Security Vulnerability29
- Logic Error10
- Hallucination5
- Ignored Instructions5
- Infinite Loop5
- Scope Explosion4
Why it happened
The underlying cause. Better distributed than failure modes, and the more useful axis if you are deciding what to guard against.
- Tool Misuse37
- Scope Misunderstanding22
- Other16
- Confidence Miscalibration13
- Logic Error13
- Instruction Misunderstanding11
- Training Data Gap8
- Context Overflow1
- Pattern Matching Error1
Where the axes cross
The same cause produces different failures, and the same failure arrives via different causes. The strongest pairings:
- Tool MisuseDestructive Action26
- Scope MisunderstandingDestructive Action18
- OtherSecurity Vulnerability9
- Tool MisuseSecurity Vulnerability9
Systemic findings
8 entries carry the catch-all classification rather than a named failure mode, and are counted here rather than among the categories above. 5 of them come from benchmarks and studies rather than a single reported incident.
Browse systemic findings →A note on one word
Logic error appears on both axes and means two different things: as a failure mode, the agent produced incorrect logic; as a root cause, faulty reasoning led to some other visible failure. The incident data is written by an automated routine and renaming it here would misrepresent the source, so the collision is stated rather than hidden.