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

MIT source entries

49 entries across 9 papers

Anwar2024Foundational Challenges in Assuring Alignment and Safety of Large Language Models73.02.00 73.02.02 73.02.03 73.05.02
Everitt2018AGI Safety Literature Review51.11.00
Gabriel2024The Ethics of Advanced AI Assistants24.09.00 24.09.05
Gipiškis2024Risk Sources and Risk Management Measures in Support of Standards for General-Purpose AI Systems62.30.02 62.31.01 62.31.02
Hammond2025Multi-Agent Risks from Advanced AI63.01.00 63.01.01 63.01.02 63.01.03 63.02.00 63.02.01 63.03.00 63.03.01 63.03.02 63.04.00 63.04.01 63.04.02 63.05.00 63.05.02 63.05.03 63.07.00 63.07.01 63.07.02 63.07.03 63.07.04 63.07.05 63.08.00 63.08.01 63.08.03 63.09.00 63.09.01 63.10.00 63.10.01 63.10.02 63.10.05
Ji2023AI Alignment: A Comprehensive Survey34.03.04
Saghiri2022A Survey of Artificial Intelligence Challenges: Analyzing the Definitions, Relationships, and Evolutions39.17.00 39.24.00
Tse2025Frontier AI Risk Management Framework (v1.0)72.03.02 72.03.03 72.04.00 72.05.13
Uuk2025A Taxonomy of Systemic Risks from General-Purpose AI61.02.38 61.02.45

Ev IDs of the entries consolidated into this risk in the MIT AI Risk Repository (V4); the source sheet row appears on hover.

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

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

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

Cross-checksframeworks mapped in to test coverage

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

See all Model & system behaviour risks →

Part of the Deployer AI Risk Register, an open-source resource powered 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.