Skip to main content
MIT AI Risk Initiative
BackDeception
Home/Risks/Hammond2025/Deception
Bargaining
Network Effects

Deception

Sub-category
Risk Domain
7AI System Safety, Failures & Limitations
7.6Multi-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.

Entity— Who or what caused the harm

Human

Due to a decision or action made by humans

AI system

Due to a decision or action made by an AI system

Other

Due to some other reason or is ambiguous

Intent— Whether the harm was intentional or accidental

Intentional

Due to an expected outcome from pursuing a goal

Unintentional

Due to an unexpected outcome from pursuing a goal

Other

Without clearly specifying the intentionality

Timing— Whether the risk is pre- or post-deployment

Pre-deployment

Occurring before the AI is deployed

Post-deployment

Occurring after the AI model has been trained and deployed

Other

Without a clearly specified time of occurrence

Part of Information Asymmetries

Other risks from Hammond2025 (42)

Miscoordination

7.6 Multi-agent risks
AI systemUnintentionalPost-deployment

Miscoordination > Incompatible strategies

7.6 Multi-agent risks
AI systemUnintentionalPost-deployment

Miscoordination > Credit Assignment

7.6 Multi-agent risks
AI systemUnintentionalPost-deployment

Miscoordination > Limited Interactions

7.6 Multi-agent risks
AI systemUnintentionalPost-deployment

Conflict

7.6 Multi-agent risks
AI systemOtherPost-deployment

Conflict > Social Dilemmas

7.6 Multi-agent risks
AI systemIntentionalPost-deployment
View all 42 risks from this paper →