Scholarlink

<p>This paper provides an overview of black-box rare-event simulation methods applicable to the safety testing of artificial intelligence agents. We explore the challenges and efficiency criteria in black-box simulation, especially emphasizing the subtle occurrence and control of underestimation errors. The paper reviews various adaptive methods, such as the cross-entropy method and adaptive multilevel splitting, highlighting both their empirical effectiveness and theoretical limitations. Additionally, it offers a comparative analysis of different confidence interval constructions for crude Monte Carlo methods, aiming to mitigate underestimation errors through effective uncertainty quantification. The paper concludes with a certifiable deep importance sampling approach, using deep neural networks to develop conservative estimators that address underestimation issues.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Black-Box Rare-Event Simulation for Safety Testing of AI Agents: An Overview

  • 期刊论文

  • 发表日期：

    2025年5月3日

查看全文
  • Yuan-Lu Bai,
  • Zhi-Yuan Huang,
  • Henry Lam,
  • Ding Zhao

摘要

This paper provides an overview of black-box rare-event simulation methods applicable to the safety testing of artificial intelligence agents. We explore the challenges and efficiency criteria in black-box simulation, especially emphasizing the subtle occurrence and control of underestimation errors. The paper reviews various adaptive methods, such as the cross-entropy method and adaptive multilevel splitting, highlighting both their empirical effectiveness and theoretical limitations. Additionally, it offers a comparative analysis of different confidence interval constructions for crude Monte Carlo methods, aiming to mitigate underestimation errors through effective uncertainty quantification. The paper concludes with a certifiable deep importance sampling approach, using deep neural networks to develop conservative estimators that address underestimation issues.