Skip to content

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

Oct 12 · Monday

Reward hacking · Papers

Found 3 papers
Filter3

Model risks

Reward hacking3

Layer

Model layer0Application layer3

System component

Guardrails and judges3Monitors3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Layer：Model layerLayer：Application layerSystem component：Guardrails and judgesTopic: Reward hackingClear all
  2. Evaluation and benchmarksarXiv 2609.34262

    论文提出基准完整性维护框架，审计 Agent 通过轨迹中的非应得通过

    审计 Agent 基准通过轨迹，区分无根据通过与奖励黑客并封堵复测

    arXiv
    2609.34262
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Opus 4.7, Opus 4.8, Opus 5 and others11
    Abstract审计通过轨迹、分开奖励黑客与验证器弱点，并用重放加现场重测验收修复。

    Scale AI 的这篇工作把 agentic benchmark 的有效性写成持续维护问题：验证器给满分，并不等于智能体展示了任务所要的能力。

    Paper analysisRead analysis
You have reached the end