# How do multi-agent systems actually fail?

Across three root causes, and the largest is the instruction rather than the model. The [MAST taxonomy](https://arxiv.org/abs/2503.13657), built from more than 1,600 annotated traces across seven multi-agent frameworks, sorts 14 named failure modes into specification and system design issues (41.77 percent: the system was told to do the wrong thing, or told imprecisely), inter-agent misalignment (36.94 percent: context lost at a handoff, agents talking past each other, conflicting outputs nobody reconciled), and task verification (21.30 percent: nothing checked whether the finished work was actually correct).

None of the three is a model-accuracy problem in the sense of the model getting a fact wrong. They're coordination and process failures: the wrong instruction going out, the wrong information crossing a seam, or no one checking the output at all. That's also why per-agent grading misses most of it: a grader that checks each agent's own output in isolation has nothing to say about a specification that was ambiguous from the start or a handoff nobody verified.

---

Sources:
- MAST, "Why Do Multi-Agent LLM Systems Fail?" (arXiv:2503.13657): https://arxiv.org/abs/2503.13657 (fetched 2026-08-25)

Source: https://tessary.ai/answers/failure-modes/how-do-multi-agent-systems-actually-fail
More on Failure modes: https://tessary.ai/answers/failure-modes
From Tessary, agent reliability for AI agents in production: https://tessary.ai