Skip to content

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

Oct 12 · Monday

Reward hacking · Papers

Found 2 papers
Filter3

Model risks

Deception and scheming2Reward hacking18

System type

Models and APIs0AI Agent4coding agent2
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Model risks：Deception and schemingSystem type：Models and APIsSystem type：coding agentTopic: Reward hackingClear all
  2. Evaluation and benchmarksarXiv 2609.39533

    CATCH：面向编码 RL 奖励作弊的可控分析测试台

    构建编码 RL 奖励作弊测试台 CATCH 并检验 CoT 监控失效

    arXiv
    2609.39533
    Published
    Layer
    Model layer
    Setting
    coding agent
    Evaluated models
    Qwen3-4B, Qwen3.5-27B
    AbstractCATCH 用双运行金标签研究编码 RL 的奖励黑客，并观察到监控会被注释适应削弱。

    CATCH 是面向编码 RL 奖励黑客的可控分析测试床，用可利用环境、可调初始倾向和基于执行的金标签，在训练全程比较黑客动态与干预。

    Paper analysisRead analysis
You have reached the end