Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter4

Impact

Unauthorized actions7Output manipulation3Availability and reliability3Oversight failure10

System type

Models and APIs4AI Agent5coding agent2science agent1Browser and computer use0

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Impact：Availability and reliabilitySystem type：coding agentSystem type：science agentSystem type：Browser and computer useClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. Risky behaviorarXiv 2610.08662

    ParanoiaEval：编码智能体不必要风险处置评测基准发布

    提出 ParanoiaEval 评测编码智能体的不必要风险处置

    arXiv
    2610.08662
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Opus-5, Sonnet-5, Sonnet-4.6 and others8
    Abstract作者用证据受控任务对评测风险处置，称其普遍、独立于任务能力并降低满意度。

    作者提出 ParanoiaEval，并称它是编码智能体风险处置能力的首个统一基准。要解决的问题是：证据已经确定风险应如何处置之后，智能体仍可能扩大验证、增加保护或备份，而现有评测要么只看功能正确性，要么把相关行为拆开研究。做法是把 NIST 的 ATMA 落到仓库任务。

    Paper analysisRead analysis
  2. Risky behaviorarXiv 2607.05462

    BioSecBench-Refusal：面向智能体生物安全风险评估的配对基准

    提出 BioSecBench-Refusal，评测智能体生物研发拒答与隐蔽危害识别

    arXiv
    2607.05462
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    Opus 4.8, Opus 4.7, Opus 4.6 and others10
    Abstract配对基准显示拒绝多由 API 触发，合法任务常被拒得不少于隐蔽危害。

    BioSecBench-Refusal 把生物研发智能体的谨慎程度和识别隐蔽危害的能力放在同一套任务上测量。

    Paper analysisRead analysis
  3. Risky behaviorarXiv 2602.00851

    研究提出说服传播现象：无关说服性对话会改变 AI Agent 的任务执行行为

    测量任务无关说服对 Agent 编码与网页研究行为的影响

    arXiv
    2602.00851
    Published
    Layer
    Application layer
    Setting
    web agent, coding agent
    Evaluated models
    gpt-4.1-nano, mistral-nemo-12b, llama-3.1-8b
    Abstract任务无关说服会在轨迹上留下任务相关的行为痕迹，但立场易感性不能稳定预测其幅度。

    这篇工作测量一件事：与任务无关的说服进入对话之后，AI 智能体执行后面的编码或网页研究时，轨迹是否系统性不同，以及“更容易被说服”能否预测差有多大。

    Paper analysisRead analysis
You have reached the end