Emergent Risks in Generative Multi-Agent Systems

Abstract

-cross Abstract: Multi-agent systems composed of large generative models are rapidly moving from laboratory prototypes to real-world deployments, where they jointly plan, negotiate, and allocate shared resources to solve complex tasks. While such systems promise unprecedented scalability and autonomy, their collective interaction also gives rise to failure modes that cannot be reduced to individual agents. Understanding these emergent risks is therefore critical. Here, we present a pioneer study of such emergent multi-agent risk in workflows that involve competition over shared resources (e.g., computing resources or market share), sequential handoff collaboration (where downstream agents see only predecessor outputs), collective decision aggregation, and others. Across these settings, we observe that such group behaviors arise frequently across repeated trials and a wide range of interaction conditions, rather than as rare or pathological cases. In particular, phenomena such as collusion-like coordination and conformity emerge with non-trivial frequency under realistic resource constraints, communication protocols, and role assignments, mirroring well-known pathologies in human societies despite no explicit instruction. Moreover, these risks cannot be prevented by existing agent-level safeguards alone. These findings expose the dark side of intelligent multi-agent systems: a social intelligence risk where agent collectives, despite no instruction to do so, spontaneously reproduce familiar failure patterns from human societies.

Authors 15

Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yuchen Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V Chawla, Nouha Dziri, Huan Sun, Xiangliang Zhang

Specification

Official page

arxiv.org/abs/2603.27771

Source:arXiv (Atom API + RSS)·T1·observed 6 h ago·high

Arxiv announce type

replace

Source:arXiv (Atom API + RSS)·T1·observed 6 h ago·high

arXiv id

2603.27771

Source:arXiv (Atom API + RSS)·T1·observed 6 h ago·high

Categories

cs.MA, cs.CL, cs.CY

Source:arXiv (Atom API + RSS)·T1·observed 6 h ago·high

PDF

arxiv.org/pdf/2603.27771

Source:arXiv (Atom API + RSS)·T1·observed 6 h ago·high

Primary category

cs.MA

Source:arXiv (Atom API + RSS)·T1·observed 6 h ago·high

Published

11 Sept 2026

Source:arXiv (Atom API + RSS)·T1·observed 6 h ago·high

Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →

Provenance