Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter4

Model risks

Deception and scheming9Reward hacking4Misalignment and value divergence3Dangerous agent actions15Dangerous capabilities8Hallucination and fabrication3

Impact

Oversight failure4

System type

Models and APIs4AI Agent8coding agent4Browser and computer use0Multi-agent systems0

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Model risks：Reward hackingSystem type：coding agentSystem type：Browser and computer useSystem type：Multi-agent systemsClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  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
  4. Evaluation and benchmarksarXiv 2608.22103

    Hack-Verifiable Terminal Bench：评测终端任务中的奖励作弊

    提出 HVTB，在终端编程任务植入蜜罐以测量奖励作弊

    arXiv
    2608.22103
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    claude-opus-5, gpt-5.6-sol, gemini-3.1-pro and others5
    Abstract用蜜罐测量终端任务上的 reward hacking，并比较五档提示词。

    HVTB 用来在真实终端与编程任务上测量 reward hacking：智能体读取被植入的参考解答或验收测试，从而偏离任务意图。作者认为这一失败模式会随智能体更自主而更重要，且事后人工或 LLM judge 可能失效。

    Paper analysisRead analysis
You have reached the end