Skip to content

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

Oct 13 · Tuesday

All papers

Found 7 papers
Filter5

System type

Models and APIs403LLM applications5AI Agent24coding agent6science agent0web agent0Multi-agent systems1Embodied systems and robotics10

Layer

Prompt layer5Model layer7Application layer252Training and data layer9
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 216papers have no tags yet and are not included in filtered results.
System type：coding agentSystem type：science agentSystem type：web agentSystem type：Multi-agent systemsLayer：Model layerClear all

Another 216papers do not have category tags yet and are not included in filtered results.

  3. InterpretabilityarXiv 2610.02702

    Study: LLM agents retain their original premises internally even when conforming to the majority

    用 J-lens 检测辩论中屈从多数的智能体是否仍内部表征原前提

    arXiv
    2610.02702
    Published
    Layer
    Model layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3.5-4B, Qwen3.6-27B, Gemma-4-E4B-it and others4

    Abstract揭示 LLM 智能体屈从多数时内部仍表征原推理前提，指出辩论表态共识可能夸大真实认同。

    Paper analysisRead analysis
  4. 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
  5. AttacksarXiv 2609.09865

    CGMIA：用成员推理攻击检测代码生成基准的数据泄漏

    提出 CGMIA，检测代码生成基准样本是否泄漏进训练集

    arXiv
    2609.09865
    Published
    Layer
    Model layer
    Setting
    coding agent
    Attacker
    Gray-box
    Evaluated models
    Qwen2.5-Coder (3B), CodeGemma (2B), DeepSeek-Coder (1.3B) and others5
    AbstractCGMIA 融合相似度、通过率、困惑度与 CodeBERT，在模拟泄漏上优于八个 MIA 基线。

    CGMIA 用成员推断检测代码生成基准是否泄入 LLM 训练集，使评测不依赖对训练语料的直接访问。

    Paper analysisRead analysis
  6. 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
  7. Evaluation and benchmarksarXiv 2605.17062

    研究复现五个前沿模型的包名幻觉：跨模型共同幻觉 127 个包名，53 个仍可被注册

    复评前沿模型代码生成中的包名幻觉与抢注攻击面

    arXiv
    2605.17062
    Published
    Layer
    Model layer
    Setting
    coding agent
    Evaluated models
    Claude Sonnet 4.6, Claude Haiku 4.5, GPT-5.4-mini and others5

    Abstract评估显示前沿模型包幻觉率收窄但威胁仍在，作者识别出跨模型通用攻击面并呼吁联合防御。

    Paper analysisRead analysis
You have reached the end