Multi-agent AI risks: what it is, and how experts rate it
Risks from multi-agent interactions, due to incentives (which can lead to conflict or collusion) and/or the structure of multi-agent systems, which can create cascading failures, selection pressures, new security vulnerabilities, and a lack of shared information and trust.
Definition and category 7.6 from the MIT AI Risk Repository, used under CC BY 4.0.
How experts rate it
With mitigations — 6.3%The difference between the two estimates — 5.9 points
Mean probability of a catastrophic outcome by 2030 — more than 1 million deaths, or more than USD 100 billion in financial loss, or comparable civilisation-scale intangible damage. Across 272 experts who took part. How this was measured
The study tabulates 5 of its 23 figures; this one was read from MIT's published chart on 18 August 2026.
Ranks 13 of 23 rated risks. This study published no interval for it, so the position of neighbouring risks is not meaningful. Experts put the difference at 5.9 percentage points.
Rank 13 of 23 by expert-rated severity, at 12.2%. See all 23 ranked
Evidence
Nothing here yet. Know of an incident, study or report? Add it.
What's been called for
Called for by 2 organisations
When AI agents cause harm, the law should be clear about who is responsible, and developers should not be able to shift that onto the businesses and people using them.
What politicians have said
Nothing here yet. Heard a politician say something about this? Add it.
What Australians say
Nothing here yet. If this matters to you, say why in a sentence.
What people ask
No questions yet. Ask one.
Think Australia should act?
Your MP and senators decide what Australia does about AI. A few lines in your own words about multi-agent AI risks is enough to tell them it matters to you.
Write to your representative