Control Charts for Multi-agent Systems

2026-05-11

AI Summary

This study addresses the lack of effective automated monitoring mechanisms in open multi-agent systems, which have traditionally relied on qualitative observation. It introduces, for the first time, adaptive control charts from process control theory to automatically monitor the evolutionary dynamics of multi-agent systems endowed with environmental learning capabilities. Combining theoretical analysis, simulation experiments, and empirical evaluation, the work not only demonstrates the necessity of adaptive control charts for monitoring learnable multi-agent systems but also uncovers a fundamental trade-off between learning capacity and adversarial robustness: while these charts effectively track normal system evolution, they remain vulnerable to slow-betrayal adversarial agents. This vulnerability delineates a theoretical boundary wherein learning and security cannot be simultaneously optimized.

Abstract

Generative agents have proven to be powerful assistants in a wide variety of contexts. Given this success, users are now deploying agents with minimal restrictions in open ended, multi-agent environments. Current methods for monitoring the dynamics of open-ended multi-agent systems are limited to qualitative inspection. In this paper, we extend the process-theoretic notion of adaptive control charts to multi-agent systems to enable automated monitoring. Using simulation, we demonstrate that adaptive control charts are necessary for monitoring multi-agent systems that can learn from their environment. We further demonstrate, both empirically and theoretically, that adaptive control charts are susceptible to adversarial agents that defect sufficiently slowly. These results illustrate a fundamental tradeoff in multi-agent system control: either agents in a system cannot learn or the system is susceptible to adversaries.

Problem

• multi-agent systems
• adaptive control charts
• adversarial agents
• automated monitoring
• system control

Innovation

• adaptive control charts
• multi-agent systems
• generative agents
• adversarial robustness
• automated monitoring