Part 3 · Operating the Fleet

Multi-Agent Systems · ~9 min

Why Multi-Agent Systems Fail

A study of 1,600+ production traces sorts the failures into three buckets — and most of them are design problems, not model problems. The prompt is the usual culprit.

Why this, for you: when a multi-agent system misbehaves, the instinct is to swap in a stronger model. The data says the bigger lever is the design: 41.8% of failures trace to design issues, not model capability. This lesson gives you the failure taxonomy as a diagnostic map and the single most common self-inflicted wound — the over-prescriptive prompt.

The Multi-Agent System Failure Taxonomy (MAST) annotated over 1,600 production traces and sorted what went wrong into three categories. Knowing which bucket a failure lands in tells you which fix to reach for.

1 The three failure categories

CategoryWhat it looks like
Specification & designBad decomposition, unclear roles, missing constraints — 41.8% of failures trace to design, not capability
Inter-agent misalignmentCommunication breakdowns, inconsistent goals, protocol violations — 36.9% of failures
Verification & terminationNo independent check, premature or never-ending stop, self-verification bias

Three more failure modes appear across every topology: self-verification bias (an agent confirms its own output — route to an independent evaluator), doom loops (10+ iterations on a broken approach — needs loop detection and budget warnings), and context blindness (acting without orientation — inject directory and tooling inventories at init).

The headline: capable frontier single-agents often match multi-agent orchestration on SE tasks while avoiding the specification complexity. Adding agents multiplies LLM calls, attack surface, and brittleness — when the quality delta over a strong single-agent is small, the cost rarely justifies it.

2 The self-inflicted wound: prescriptive prompts

Subagents receive only their own system prompt and the delegation message — not the lead's full context. So minor wording changes in the lead's prompt cascade unpredictably. Anthropic observed it directly: "small changes to the lead agent can unpredictably change how subagents behave." This isn't a bug — it's a property of systems where agents interpret instructions rather than execute them.

Prompt styleCascade behavior
Prescriptive — step-by-step, exact formatsBrittle — small changes break downstream agents
Framework — principles, effort budgets, heuristicsResilient — subagents adapt within boundaries

A framework prompt defines division of labor, problem-solving heuristics, effort budgets, and quality criteria — what "done" looks like, not how to get there. Effective multi-agent prompts encode "heuristics rather than rigid rules."

# prescriptive — adding "thorough" makes subagents over-scale unpredictably "Thoroughly review every file for correctness, security, performance. List all findings." # framework — the effort budget caps behavior regardless of adjective "Review changed files only. Max 5 findings per category. One pass. Return structured JSON."

3 The mitigations that actually moved the number

Harness changes beat model changes

Loop detection, pre-completion checklists, and prompt adjustments — all harness-level, no model change — collectively produced a 13.7-point improvement on Terminal-Bench 2.0. The fixes for multi-agent failure live in the environment and the prompts, not in a bigger model.

↪ Your win: diagnose the bucket, fix the design

Retrieval practice — recall, don't peek

Question 1The MAST taxonomy was built by annotating…

Question 2A large share of multi-agent failures trace to…

Question 3Compared with prescriptive prompts, framework prompts are…

Question 4Without explicit effort budgets, a research system once spawned…

Question 5 · spaced recall from Lesson 6Admission control fixes self-judgement bias by making "done" decided by…

Ask me anything. Want help rewriting a prescriptive orchestrator prompt into a framework prompt with explicit effort budgets, or classifying a failure you've hit into the three MAST buckets? Next in Part 3: Rainbow Deployments — shipping new agent versions without breaking live sessions.
✎ Feedback