[2502.14143] Multi-Agent Risks from Advanced AI
Abstract:The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These systems pose novel and under-explored risks. In this report, we provide a structured taxonomy of these risks by identifying three key failure modes (miscoordination, conflict, and collusion) based on agents' incentives, as well as seven key risk factors (information asymmetries, network effects, selection pressures, destabilising dynamics, commitment problems, emergent agency, and multi-agent security) that can underpin them. We highlight several important instances of each risk, as well as promising directions to help mitigate them. By anchoring our analysis in a range of real-world examples and experimental evidence, we illustrate the distinct challenges posed by multi-agent systems and their implications for the safety, governance, and ethics of advanced AI.
[2502.14143] Multi-Agent Risks from Advanced AI --> Computer Science > Multiagent Systems arXiv:2502.14143 (cs) [Submitted on 19 Feb 2025] Title: Multi-Agent Risks from Advanced AI Authors: Lewis Hammond , Alan Chan , Jesse Clifton , Jason Hoelscher-Obermaier , Akbir Khan , Euan McLean , Chandler Smith , Wolfram Barfuss , Jakob Foerster , Tomáš Gavenčiak , The Anh Han , Edward Hughes , Vojtěch Kovařík , Jan Kulveit , Joel Z. Leibo , Caspar Oesterheld , Christian Schroeder de Witt , Nisarg Shah , Michael Wellman , Paolo Bova , Theodor Cimpeanu , Carson Ezell , Quentin Feuillade-Montixi , Matija
Explore this link on the map →saved by
related reading
- [2602.12316] GT-HarmBench: Benchmarking AI Safety Risks Through the Lens of Game Theoryarxiv.org
- Lessons from Moltbook and OpenClaw: The Agentic Internet’s Trust Problem - Irregularirregular.com
- Dario Amodei — The Adolescence of Technologydarioamodei.com
- Why multi-agent safety is important — LessWronglesswrong.com
- Cooperative AIcooperativeai.com
- Red-teaming a network of agents: Understanding what breaks when AI agents interact at scale - Microsoft Researchmicrosoft.com
- How we built our multi-agent research system \ Anthropicanthropic.com
- Getting Up to Speed on Multi-Agent Systems, Part 1: The Landscapechristophermeiklejohn.com
- The Pieces of The Loop - by Interesting Engineering ++interestingengineering.substack.com
- Oxford Witt Labwittlab.ai
- ROGUE:arxiv.org
- What failure looks like — LessWronglesswrong.com