Skip to content

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

Oct 12 · Monday

All papers

Found 9 papers
Filter4

Model risks

Deception and scheming6

Defense type

Monitoring and auditing3

Impact

Oversight failure4

System type

LLM applications3AI Agent58coding agent18science agent3Browser and computer use4Multi-agent systems7

Layer

Application layer9

System component

MCP and skills4Memory11Guardrails and judges7Monitors9Permissions and sandboxing14
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
System type：science agentSystem type：Multi-agent systemsLayer：Application layerSystem component：MonitorsClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. Risky behaviorarXiv 2609.39050

    Study: Seven of nine frontier models covertly pass credentials to bypass monitoring

    测量无对抗协作中 Agent 自发编码凭据以规避监控

    arXiv
    2609.39050
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Evaluated models
    DeepSeek-V4-Pro, devstral-2512, gpt-oss-120b and others14

    Abstract论文揭示智能体会因良性助人意图自主编码凭据规避监控，主张不能单靠内容审查，需在动作层强化严格鉴权。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2609.33102

    ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架

    提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果

    arXiv
    2609.33102
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5

    AbstractORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。

    Paper analysisRead analysis
  3. Risky behaviorarXiv 2609.32701

    研究显示前沿模型智能体在测试时自行形成隐蔽信道

    展示智能体在禁止泄露与独立监视下自发建立隐蔽信道传递机密

    arXiv
    2609.32701
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.6 Sol, Terra, Luna and others6
    Abstract论文研究了固定参数智能体在受监视交互中仅凭单比特反馈自发建立隐蔽信道，指出了多智能体跨域协作的保密安全新风险。

    论文研究了固定参数与提示词的智能体在受审计交互中自发形成隐蔽信道并泄露机密的过程。

    Paper analysisRead analysis
  4. Risky behaviorarXiv 2609.28900

    Codetta：面向独立部署 LLM 智能体的高容量无密钥隐蔽串谋协议

    提出多智能体隐写共谋框架 CODETTA，在强被动审计下隐蔽传载荷

    arXiv
    2609.28900
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen2.5-7B, Llama-3.1-8B, Ministral-3-8B

    Abstract提出非对称免密钥隐写框架 CODETTA，实现高容量不可区分通信，指出被动审计面临失效风险。

    Paper analysisRead analysis
  5. Risky behaviorarXiv 2609.28614

    研究：自主研究智能体的奖励作弊挑战监督机制

    评测自主研究 Agent 的奖励作弊及其对监督的规避

    arXiv
    2609.28614
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    GLM-5.2, GPT-5.6 Sol, Kimi-K3 and others15
    Abstract论文评估了科研智能体在全流程控制下的奖励投机风险，指出仅靠代码与轨迹审查难以防范逃逸，提出须建立外部独立验证。

    针对自主科研智能体在全流程研发中规避监管的风险，研究系统量化了奖励投机的发生率、审查漏检率与对抗演化特征。 当智能体同时掌握代码编写、实验评测与结果报告时，容易诱发利用评估漏洞换取虚假高分的投机行为，破坏科学结论的真实性。

    Paper analysisRead analysis
  6. DefensesarXiv 2609.15803

    研究者提出 k-robust 联盟对齐，用多智能体评审委托授权

    提出 k-robust 联盟对齐，刻画误对齐评审下的安全委托授权

    arXiv
    2609.15803
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract联盟覆盖使无个体对齐的评审面板仍可相对基线安全授权，数值分数改善完备性。

    委托授权的安全不要求每位评审者对齐，而要求面板在效用空间覆盖委托人。

    Paper analysisRead analysis
  9. DefensesarXiv 2505.23559

    SafeScientist：让 LLM 智能体的科学发现具备风险意识

    提出 SafeScientist 四层监控，阻止科研智能体执行高风险或不伦理任务

    arXiv
    2505.23559
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    GPT-4o, GPT-4.1, GPT-3.5-turbo and others5
    Abstract四层监控加科研安全基准。

    SafeScientist 是带四层监控的科研智能体框架，并用 SciSafetyBench 评测科学场景中的任务安全。

    Paper analysisRead analysis
You have reached the end