Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

Reward hacking · Papers

Found 1 paper
Filter1

Layer

Application layer1Training and data layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Layer：Application layerTopic: Reward hackingClear all
  1. Analysis and theoryarXiv 2609.32390

    基于 2026 年 Hugging Face 事件的奖励作弊与 Agent 围堵失效蒙特卡洛研究

    用五阶段蒙特卡洛分析奖励作弊如何导致 Agent 围堵失效

    arXiv
    2609.32390
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Abstract分层控制的模拟事件率低于弱控制以及单独隔离或单独监控。

    这项研究用蒙特卡洛把奖励黑客接到外部安全事件上，比较的是控制组合，不是 Hugging Face 事件的再现概率。

    Paper analysisRead analysis
You have reached the end