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 scheming9Reward hacking11Misalignment and value divergence3Dangerous agent actions17Dangerous capabilities8

System type

AI Agent19coding agent3Multi-agent systems8

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 273papers have no tags yet and are not included in filtered results.
Model risks：Misalignment and value divergenceSystem type：coding agentLayer：Application layerClear all

Another 273papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.32616

    Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

    提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作

    arXiv
    2609.32616
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14

    Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。

    Paper analysisRead analysis
You have reached the end