arXiv cs.MA· Hayden Helm, Carey Priebe, Brandon Duderstadt·· 11 小时前AI 评分34
多智能体系统的自适应控制图监控研究
Control Charts for Multi-agent Systems
AI 导读
研究者将自适应控制图引入多智能体系统，实现开放式多智能体环境的自动化监控。模拟实验表明，能从环境学习的多智能体系统必须使用自适应控制图；但自适应控制图对缓慢叛变的对抗性智能体存在脆弱性。这揭示了多智能体系统控制的根本权衡：固定基线监控会误报正常学习行为，自适应基线监控则放行缓慢作恶者。
正文 · 原文
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 aggregate statistics, qualitative inspection, or detecting change between two fixed timepoints. 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 suggest a fundamental tradeoff in multi-agent system control: monitors with fixed baselines flag legitimate learning, while monitors with adaptive baselines admit slow adversaries. We conjecture this holds for any monitor.
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.11135 [cs.MA] |
| (or arXiv:2605.11135v2 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2605.11135 arXiv-issued DOI via DataCite |
Submission history
From: Hayden Helm [view email]
[v1]
Mon, 11 May 2026 18:42:12 UTC (1,423 KB)
[v2]
Thu, 5 Nov 2026 20:04:01 UTC (1,682 KB)
来源：arXiv cs.MA · arxiv.org