Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Model risks

Deception and scheming21Reward hacking16Misalignment and value divergence10Dangerous agent actions24Dangerous capabilities10Inappropriate refusal3Hallucination and fabrication6

System type

Models and APIs61AI Agent9coding agent2Multi-agent systems1Embodied systems and robotics3
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：Inappropriate refusalSystem type：coding agentSystem type：Multi-agent systemsClear all

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

  1. Risky behaviorarXiv 2609.27900

    论文揭示多智能体委派结构放大 LLM 安全风险

    评测多智能体委托结构如何放大模型的安全拒答失效

    arXiv
    2609.27900
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Claude-Sonnet-4.6, GPT-5, Gemini-3.1-Pro and others6

    Abstract论文揭示多智能体层级委托会导致单模型安全对齐失效，多项前沿模型有害执行大幅增加且单层防御难以奏效。

    Paper analysisRead analysis
  2. InterpretabilityarXiv 2606.05396

    研究用消融移除代码 LLM 拒答方向，分离拒答与生成能力

    用 abliteration 消融代码 LLM 拒答方向，分离拒答与漏洞注入能力

    arXiv
    2606.05396
    Published
    Layer
    Model layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-Coder-Instruct 3B, Qwen2.5-Coder-Instruct 7B, Qwen2.5-Coder-Instruct 14B
    Abstract拒答可用低秩编辑去掉，CWE-89 注入是否成功仍由模型规模决定。

    这项初步可行性研究用 abliteration 把代码 LLM 的拒答和 CWE 注入能力拆开：意愿可以被低秩编辑解锁，注入是否成功仍看参数规模。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2605.19722

    研究用 30 项漏洞分析任务评测自主安全智能体的安全对齐效果

    评测自主安全智能体在授权漏洞分析中的对齐拒答效应

    arXiv
    2605.19722
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Gemma 4 31B official instruction-tuned model, TrevorJS Gemma 4 31B uncensored GGUF, Gemma 4 26B A4B official instruction-tuned model and others8
    Abstract轨迹级评测把拒答、接地、工具接口分开。

    这项工作把安全对齐效应测成自主安全智能体的轨迹属性，而不是单轮拒答率。

    Paper analysisRead analysis
You have reached the end