Failure Modes: Why Agents Break
MASFT (Berkeley, 2025) catalogs 14 multi-agent failure modes in 3 categories. Microsoft's Taxonomy documents how existing AI failures amplify in agentic settings. Industry field data converges on five recurring modes: hallucinated actions, scope creep, cascading errors, context loss, tool misuse. Name MASFT's three failure categories and at least four specific modes in each. Explain why agentic failure amplifies existing AI failure modes (bias, hallucination). Describe the five industry-recurring modes and their mitigations. Implement a stdlib detector that tags agent traces with failure-mode labels. Teams ship agents that work on 90% of traces. The 10% failures are not random noise — they fall into a small number of recurring categories. Once you can name them, you can monitor for them and fix them. Multi-Agent System Failure Taxonomy. 14 failure modes clustered into 3 categories. Inter-annotator Cohen's Kappa 0.88 — the categories are reliably distinguishable. Central claim: failures are fundamental design flaws in multi-agent systems, not LLM limitations to be fixed with better base models. Existing AI failures (bias, hallucination, data leakage) amplify in agentic settings. New failures emerge from autonomy: unintended action at scale, tool misuse, mission drift. The whitepaper is the risk register for agentic products. Failures arise from orchestration, internal state evolution, and environment interaction. Not just "bad code" or "bad model output.". Two primary manifestations: Instruction-following Deviation —…
Failure Modes: Why Agents Break: MASFT (Berkeley, 2025) catalogs 14 multi-agent failure modes in 3 categories. Microsoft's Taxonomy documents how existing AI…
This free lesson is part of the AI Engineering from Scratch curriculum. Read the full explanation, run the lesson code, and verify the result in the interactive reader or from the repository source.
Browse the complete course catalog or open this lesson on GitHub.