MR-057 Model & system behaviour Both scope

Multi-agent interaction risks

Interactions among multiple AI agents cause miscoordination, collusion, cascading or destabilizing dynamics (e.g. flash crashes).

Risk family: Model & system behaviour
MIT domain: 7. AI System Safety, Failures, & Limitations
MIT subdomain: 7.6 > Multi-agent risks
AI type: Agentic, GPAI
Scope: Both
Source standard: MIT AI Risk Repository v4

Provenance

Source standard

MIT AI Risk Repository v4

Source frameworks

9 source framework citation keys

Anwar2024, Everitt2018, Gabriel2024, Gipiškis2024, Hammond2025, Ji2023, Saghiri2022, Tse2025, Uuk2025

ISO/IEC references

23894 obj A.9, A.10; src 8; mech B.2 | 42001 ctrl A.6.2.6

Framework crosswalk

Every framework item mapped to this risk. Items marked partial overlap only in part; definitions appear on hover where the source licence permits.

Sourcesframeworks that contributed to the register

ISO 238942

A.10 ISO/IEC 23894 Annex A A.10
A.9 ISO/IEC 23894 Annex A A.9

ISO 420011

A.6.2.6 ISO/IEC 42001 Annex A A.6.2.6

Cross-checksframeworks mapped in to test coverage

OWASP Agentic2

ASI07 Insecure Inter-Agent Communication
ASI08 Cascading Failures

More in Model & system behaviour

MR-001 MR-002 MR-003 MR-004 MR-005 MR-006 MR-007 MR-008 MR-019 MR-021 MR-022 MR-023 MR-025 MR-026 MR-027 MR-028 MR-029 MR-031 MR-049 MR-050 MR-051 MR-052 MR-053 MR-055 MR-056 MR-058 MR-059 MR-061

Part of the Deployer AI Risk Register, an open-source resource developed by MindXO. Version 1.0, 3 July 2026. Derived from the MIT AI Risk Repository (V4, December 2025) under CC BY 4.0; an independent derivative work, not endorsed by or affiliated with MIT. Sub-risk decomposition references MITRE ATLAS™ v5.6.0 (© 2021-2026 The MITRE Corporation, reproduced and distributed with permission). ISO/IEC and EU AI Act references are by number only. License: CC BY 4.0. Full attribution and licensing.