执法智能体:增强多智能体AI框架中的问责性与韧性
Enforcement Agents: Enhancing Accountability and Resilience in Multi-Agent AI Frameworks
AI总结:
本文提出执法智能体(EA)框架,通过嵌入监督智能体实现多智能体系统的实时监控与纠正,实验表明增加EA可显著提升任务成功率、运行寿命和恶意智能体改造率。
摘要:
随着自主智能体变得更加强大并被广泛使用,确保它们安全运行并与系统目标保持一致变得日益重要,尤其是在多智能体环境中。当前系统通常依赖智能体自我监控或事后纠正问题,但缺乏实时监督机制。本文提出了执法智能体(Enforcement Agent,EA)框架,该框架在环境中嵌入专门的监督智能体,以监控其他智能体、检测不当行为并通过实时纠正进行干预。我们在一个定制的无人机仿真中实现了该框架,并在90个回合中分别使用0个、1个和2个EA配置进行了评估。结果表明,增加EA显著提升了系统安全性:成功率从无EA时的0.0%上升到使用一个EA时的7.4%,并在使用两个EA时达到26.7%。该系统还表现出更长的运行寿命和更高的恶意无人机改造率。这些发现凸显了轻量级实时监督在增强多智能体系统对齐性和韧性方面的潜力。
英文摘要:
As autonomous agents become more powerful and widely used, it is becoming increasingly important to ensure they behave safely and stay aligned with system goals, especially in multi-agent settings. Current systems often rely on agents self-monitoring or correcting issues after the fact, but they lack mechanisms for real-time oversight. This paper introduces the Enforcement Agent (EA) Framework, which embeds dedicated supervisory agents into the environment to monitor others, detect misbehavior, and intervene through real-time correction. We implement this framework in a custom drone simulation and evaluate it across 90 episodes using 0, 1, and 2 EA configurations. Results show that adding EAs significantly improves system safety: success rates rise from 0.0% with no EA to 7.4% with one EA and 26.7% with two EAs. The system also demonstrates increased operational longevity and higher rates of malicious drone reformation. These findings highlight the potential of lightweight, real-time supervision for enhancing alignment and resilience in multi-agent systems.
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。