arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.14972cs.CL
收藏

AgentMonitor:一个用于预测和安全多智能体系统的即插即用框架

AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems

Hong Kong University of Science and Technology(香港科技大学);Tsinghua University(清华大学)

Chi-Min Chan, Jianxuan Yu, Weize Chen, Chunyang Jiang, Xinyu Liu, Weijie Shi, Zhiyuan Liu, Wei Xue, Yike Guo

AI总结:

提出AgentMonitor框架,在智能体级别捕获输入输出并训练回归模型以预测多智能体系统任务性能,同时实时校正恶意智能体行为,实验显示高预测相关性并显著提升系统安全性与可靠性。

摘要:

大型语言模型(LLMs)的快速发展促成了基于LLM的智能体的兴起。近期研究表明,每个智能体扮演特定角色的多智能体系统(MAS)能够优于单个LLM。然而,为任务配置MAS仍然具有挑战性,其性能仅在执行后可观察。受LLM开发中缩放定律的启发,我们研究了MAS性能是否可以事先预测。我们引入了AgentMonitor,这是一个在智能体级别集成以捕获输入和输出的框架,将其转换为统计数据,用于训练回归模型以预测任务性能。此外,它还可以进一步应用实时校正,以解决恶意智能体带来的安全风险,减轻负面影响并增强MAS安全性。实验表明,XGBoost模型在域内实现了0.89的Spearman相关性,在更具挑战性的场景中为0.58。此外,使用AgentMonitor平均减少了6.2%的有害内容,增加了1.8%的有益内容,提升了安全性和可靠性。代码可在\url{https://github.com/chanchimin/AgentMonitor}获取。

英文摘要:

The rapid advancement of large language models (LLMs) has led to the rise of LLM-based agents. Recent research shows that multi-agent systems (MAS), where each agent plays a specific role, can outperform individual LLMs. However, configuring an MAS for a task remains challenging, with performance only observable post-execution. Inspired by scaling laws in LLM development, we investigate whether MAS performance can be predicted beforehand. We introduce AgentMonitor, a framework that integrates at the agent level to capture inputs and outputs, transforming them into statistics for training a regression model to predict task performance. Additionally, it can further apply real-time corrections to address security risks posed by malicious agents, mitigating negative impacts and enhancing MAS security. Experiments demonstrate that an XGBoost model achieves a Spearman correlation of 0.89 in-domain and 0.58 in more challenging scenarios. Furthermore, using AgentMonitor reduces harmful content by 6.2% and increases helpful content by 1.8% on average, enhancing safety and reliability. Code is available at \url{https://github.com/chanchimin/AgentMonitor}.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑