MIT AI Risk Repository · domain 7: AI system safety, failures, & limitations
7.6 Multi-agent risks
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.
- 53
- 5
- —
- —
| Label | Value |
|---|---|
| AI | 35 |
| Other | 15 |
| Human | 3 |
| Label | Value |
|---|---|
| Unintentional | 23 |
| Other | 15 |
| Intentional | 15 |
| Label | Value |
|---|---|
| Post-deployment | 44 |
| Other | 8 |
| Pre-deployment | 1 |
| Label | Value |
|---|---|
| Risk Category | 11 |
| Risk Sub-Category | 42 |
Risk entries
Browse and export all- Multi-agent collusion propensity:
"Multiple agents tend to coordinate actions through covert means to maximize common interests (possibly harming third-party interests or evading regulation), even if individual agents are designed wit...
- Pattern recognition capability
"AI models and systems could exacerbate financial bubbles by reinforcing market trends."
- Trading capabilities
"AI may contribute to increased market volatility by accelerating transactions and influencing financial trends in unpredictable ways."