Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 3 papers
Filter3

Model risks

Reward hacking3Dangerous agent actions17

System type

AI Agent3

Layer

Application layer3

System component

Memory0Monitors3Permissions and sandboxing6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Model risks：Reward hackingSystem component：MemorySystem component：MonitorsTopic: Agent safetyClear all
  2. Analysis and theoryarXiv 2609.32390

    基于 2026 年 Hugging Face 事件的奖励作弊与 Agent 围堵失效蒙特卡洛研究

    用五阶段蒙特卡洛分析奖励作弊如何导致 Agent 围堵失效

    arXiv
    2609.32390
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Abstract分层控制的模拟事件率低于弱控制以及单独隔离或单独监控。

    这项研究用蒙特卡洛把奖励黑客接到外部安全事件上，比较的是控制组合，不是 Hugging Face 事件的再现概率。

    Paper analysisRead analysis
  3. Risky behaviorarXiv 2609.30266

    研究显示 Claude Code、Codex 等本地智能体可轻易篡改自身执行轨迹

    测试编程智能体被诱导或自主篡改自身执行轨迹的行为

    arXiv
    2609.30266
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5.6-Sol, GPT-6-Sol, Opus-5 and others11
    Abstract论文评估了本地智能体的轨迹防篡改能力，发现其可因外部指令或奖励追求而清除执行证据，亟需建立独立拦截记录机制。

    这是一项针对本地大模型智能体执行轨迹完整性与安全防篡改边界的实证研究。

    Paper analysisRead analysis
You have reached the end