https://taxonomy.eticas.ai/risk/multi-step-actions
Maturity: emerging
AI systems that plan and execute sequences of actions, where errors in early steps cascade unpredictably through later steps.
This subcategory is emerging. It has not yet been validated through established assessment methods.
System type: Large language models (LLM)
Lifecycle stages: Post Processing
| Framework | Reference |
|---|---|
| AIUC-1 — AI Underwriting Company Standard | Prevent unauthorized AI agent actions |
| Framework | Reference |
|---|---|
| MIT AI Risk Repository | Multi-agent risks |