# 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.

Canonical: https://www.zambrite.com/ai-training/lessons/agent-failure-modes

A9Advanced 60 minutes reading and codeUnlocked

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.

## Learning Objectives

- 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.

## The Problem

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.

## The Concept

### MASFT (Berkeley, arXiv:2503.13657)

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.

### Microsoft Taxonomy of Failure Mode in Agentic AI Systems

- 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.

### Characterizing Faults in Agentic AI (arXiv:2603.06847)

- Failures arise from orchestration, internal state evolution, and environment interaction. 
- Not just "bad code" or "bad model output."

### LLM Agent Hallucinations Survey (arXiv:2509.18970)

Two primary manifestations:

- **Instruction-following Deviation** — agent doesn't follow the system prompt. 
- **Long-range Contextual Misuse** — agent forgets or misapplies context from earlier turns.

Sub-intention errors: Omission (missed step), Redundancy (repeated step), Disorder (out-of-order steps).

### The five industry-recurring modes

Arize, Galileo, NimbleBrain 2024-2026 field analyses converge on:

- **Hallucinated actions.** Agent invokes a tool that doesn't exist or fabricates arguments. 
- **Scope creep.** Agent expands task beyond the user's ask (creates extra PRs, sends extra emails). 
- **Cascading errors.** One wrong call triggers downstream effects. A phantom SKU hallucination triggers four API calls — a multi-system incident. 
- **Context loss.** Long-horizon tasks forget early-turn constraints. 
- **Tool misuse.** Calls the right tool with wrong arguments, or the wrong tool entirely.

Cascading is the killer. Agents cannot distinguish "I failed" from "the task is impossible" and often hallucinate a success message on 400 errors to close the loop.

### Mitigation: gates at every step

Automated verification gates at every step of a reasoning chain, checking factual grounding against environment state. Concretely:

- Per-step safety classifier (Lesson 21). 
- Tool-call argument validation (Lesson 06). 
- Cross-check retrieved content against known facts (Lesson 05, CRITIC). 
- Detect success hallucination by re-probing state (was the file actually created?).

### Where failure monitoring goes wrong

- **Tagging only crashes.** Most agent failures produce valid-looking output. Need content-level checks. 
- **No baseline.** Drift detection needs a last-known-good; without it you cannot say "this is getting worse." 
- **Over-alerting.** Every failure produces a page. Cluster and rate-limit.

## Build it

`code/main.py` implements a stdlib failure-mode tagger:

- A synthetic trace dataset covering the five modes. 
- Detector functions per mode (signature patterns on tool calls, outputs, repeat actions). 
- A tagger that labels each trace and reports mode distribution.

Run it:

```
python3 code/main.py
```

Output: per-trace labels + aggregate distribution, a cheap reproduction of what Phoenix's trace clustering surfaces.

## Use it

- **Phoenix** for production drift clustering (Lesson 24). 
- **Langfuse** for session replay + annotation. 
- **Custom** for domain-specific signatures your observability platform can't detect.

## Exercises

- Add a detector for "success hallucination": agent returns success but the target state is unchanged. 
- Tag 100 real traces from a product you've built. Which mode dominates? What's the cost of fixing it? 
- Implement a "cascade radius" metric: given a failure at step N, how many downstream steps did it affect? 
- Read MASFT's 14 failure modes. Pick three that apply to your product. Write detectors. 
- Wire one detector into a CI job: fail the build if \>=5% of traces tag a mode.

## Key Terms

| Term | What people say | What it actually means |
| --- | --- | --- |
| MASFT | "Multi-agent failure taxonomy" | Berkeley 14-mode categorization |
| Cascading error | "Ripple failure" | One early mistake propagates through N steps |
| Context loss | "Forgot the constraint" | Long-horizon turn drops early-turn facts |
| Tool misuse | "Wrong tool / wrong args" | Valid call, wrong invocation |
| Success hallucination | "Faked completion" | Agent claims success on a 400; state unchanged |
| Scope creep | "Overreach" | Agent does more than asked |
| Instruction-following deviation | "Disobedience" | Ignores system prompt or user constraint |
| Sub-intention errors | "Plan bugs" | Omission, redundancy, disorder in plan execution |

## Further Reading

- [Cemri et al., MASFT (arXiv:2503.13657)](https://arxiv.org/abs/2503.13657) — 14 failure modes, 3 categories 
- [Microsoft, Taxonomy of Failure Mode in Agentic AI Systems](https://cdn-dynmedia-1.microsoft.com/is/content/microsoftcorp/microsoft/final/en-us/microsoft-brand/documents/Taxonomy-of-Failure-Mode-in-Agentic-AI-Systems-Whitepaper.pdf) — risk register 
- [Arize Phoenix](https://docs.arize.com/phoenix) — drift clustering in practice 
- [Anthropic, Building Effective Agents](https://www.anthropic.com/research/building-effective-agents) — when simpler patterns avoid modes entirely

## The code

### The lesson’s full source

The complete runnable files this lesson builds.

Milestone for[An observable back-office agent](https://www.zambrite.com/ai-training/lessons/capstone-back-office-agent)

## Break it on purpose

Build a failure suite from real statement mess: duplicate payments, partial payments, reversed transactions, two customers sharing a phone, and the agent claiming a match it never verified. Record how each is detected.

### Done when

- At least 25 failure cases: duplicates, partials, reversals, shared phones, false completion
- Detection of false completion claims by checking tool evidence
- Pass rate per failure type, at least 90% overall

Stretch: Add a chaos mode that injects tool failures at random

## Interview practice

Questions on this topic that AI engineering interviews ask, with the companies reported to ask them. Answer the way you would out loud; your answer is scored against production standards with concrete guidance on what to improve.

[A8 Orchestration Patterns: Supervisor, Swarm, Hierarchical](https://www.zambrite.com/ai-training/lessons/orchestration-patterns)[Next · A10 Prompt Injection and the PVE Defense](https://www.zambrite.com/ai-training/lessons/prompt-injection-defence)

Adapted from open-source work: AI Engineering from Scratch by Rohit Ghumare (MIT, lesson text, code and quizzes); Awesome LLM Apps by Shubham Saboo (Apache-2.0, starter code); AI Engineering Interview Questions by Outcome School (Apache-2.0, interview questions). Capstones, milestones, data packs and Zambian context by Zambrite.

## Related
- [Home](https://www.zambrite.com/)
- [Contact](https://www.zambrite.com/contact)