Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter5

Model risks

Reward hacking5Misalignment and value divergence2Dangerous agent actions22Dangerous capabilities0Inappropriate refusal3

Defense type

Model hardening36Inference-time intervention7Detection and filtering5Instruction–data separation2Permissions and approval5Monitoring and auditing10

Impact

Oversight failure4

System type

AI Agent7

Layer

Application layer7

System component

Permissions and sandboxing5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
Model risks：Reward hackingModel risks：Misalignment and value divergenceModel risks：Dangerous capabilitiesDefense type：Instruction–data separationDefense type：Permissions and approvalClear all

Another 262papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2610.11754

    仅凭输出审查无法验证什么：面向研究智能体的研究契约

    提出研究合同，把已批准选择绑定到执行证据并由检查器核验

    arXiv
    2610.11754
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    OpenAI gpt-5.6-sol, OpenAI gpt-5.6-terra, OpenAI gpt-5.6-luna and others18
    Abstract研究合同暴露四类输出单独建不立的关系。

    研究合同用来核验计算科学研究智能体是否仍在已批准研究之内，不判断科学是否为真。。

    Paper analysisRead analysis
  3. DefensesarXiv 2610.05162

    MemAdapter：用反事实适配缓解记忆诱发的谄媚

    提出 MemAdapter，在检索后约束记忆对智能体推理的影响

    arXiv
    2610.05162
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V4-Flash, GPT-5.6-sol, Qwen3-8B
    Abstract检索后三阶段调节记忆角色。

    MemAdapter 是给长期记忆智能体用的检索后调节框架，用来处理记忆诱发谄媚。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.36170

    Assay：用内容寻址证据图约束 AI 编码智能体的声明失效

    提出 Assay，用依赖锥哈希绑定代码断言并在合并门禁拦截失效声明

    arXiv
    2609.36170
    Published
    Layer
    Application layer
    Setting
    coding agent
    AbstractAssay 提供随依赖内容失效的证据管理。

    Assay 是一套面向 AI 辅助软件交付的内容寻址证据系统，关注代码改变后，测试通过、无秘密或行为保持等断言还能否用于批准合并。

    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
  7. DefensesarXiv 2602.03224

    TAME: Trustworthy Agent Memory Test-time Evolution and Systematic Benchmarking

    提出 TAME 调节 Agent 测试时记忆演化，并用 Trust-Memevo 评测可信度

    arXiv
    2602.03224
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen3-32B, GPT-5.2
    AbstractTAME 在共享记忆上同时调节效用与信任。

    TAME 针对测试时记忆演化中的 Agent Memory Misevolution：良性任务只按成败保留经验时，任务表现可以上升，安全、隐私、公平等可信度下降或随领域波动。

    Paper analysisRead analysis
You have reached the end