Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter2

Model risks

Deception and scheming5Reward hacking4Dangerous agent actions9Dangerous capabilities8

Defense type

Monitoring and auditing4

Impact

Oversight failure3

System type

Models and APIs5AI Agent16coding agent5Multi-agent systems3

Layer

Application layer4

System component

Monitors5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Model risks：Deception and schemingSystem type：coding agentClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. 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 2605.16626

    Sleight-Bench: 20 of 40 attacks were never detected by Opus 4.6 monitoring.

    构建 SLEIGHT-Bench 评测代码智能体监控对概念盲点规避的捕获

    arXiv
    2605.16626
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude Opus 4.6, Claude Opus 4.7, Claude Sonnet 4.6 and others6

    Abstract评估针对监控盲点的规避基准，发现前沿监控器漏报率高，算力与脚手架虽有提升但存在类别局限。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2510.09462

    研究者用提示注入攻击监控模型，绕过 AI 控制协议

    提出针对可信监控器的自适应提示注入，绕过 AI 控制协议

    arXiv
    2510.09462
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-4o, GPT-4, GPT-4.1 and others4

    Abstract作者指出当前依赖 LLM 监控器的 AI 控制协议易被自适应提示注入攻破，呼吁引入多监控器集成与数据流隔离机制。

    Paper analysisRead analysis
You have reached the end