Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter3

Impact

Harmful content15Unauthorized actions16Data and privacy leaks22Output manipulation96Availability and reliability6Oversight failure15

System type

Models and APIs35LLM applications4AI Agent52coding agent10web agent4Multi-agent systems2Embodied systems and robotics12

Layer

Application layer5
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：LLM applicationsSystem type：Multi-agent systemsClear all

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

  2. Evaluation and benchmarksarXiv 2610.04691

    RAGStress：评测知识库退化下 RAG 鲁棒性的受控基准

    提出 RAGStress 受控基准，评测知识库退化下的 RAG

    arXiv
    2610.04691
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Claude Sonnet 4, Claude Opus 4.6, DeepSeek R1 and others5
    Abstract作者用 RAGStress 比较五系统。

    RAGStress 是知识库损坏下的 RAG 受控压力测试。作者明确不把它当作模型排行榜。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2610.02874

    SceneFactory-3D：将 2D 交通场景提升为 3D 物理反事实以做安全评测

    提出 SceneFactory-3D，用路况反事实评测驾驶策略的闭环安全性

    arXiv
    2610.02874
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics, Multi-agent systems
    Evaluated models
    Frozen L0, L0-T, L1 and others5
    AbstractSceneFactory-3D 固定场景只改路况。

    SceneFactory-3D 是 GPU 批处理的多智能体驾驶仿真器，用来在场景和控制器固定时只改路面物理，并比较闭环结果。

    Paper analysisRead analysis
  4. Risky behaviorarXiv 2609.35928

    论文发现暴露模型身份标签会削弱多智能体 LLM 合作

    发现暴露模型家族标签会让多智能体派系化并削弱合作

    arXiv
    2609.35928
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Gemma (gemma-4-26B-A4B-it), GPT-OSS (gpt-oss-20b), Nemotron (NVIDIA-Nemotron-3-Nano-30B-A3B-BF16) and others6
    Abstract可见身份标签让异构 LLM 群体按标签结派，共识更慢、更贵，去掉标签后该行为消失。

    Del Giudice 等人研究异构多智能体 LLM 系统里一个配置细节：把模型家族身份告诉智能体，会不会改变合作。他们把由此出现的、按身份结组的倾向称为 factionalism。任务是无利害的共同决策，没有人设，也没有偏向同家族同伴的奖励。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2609.15017

    PIDS-Bench：在过度防御、混淆与分布偏移下评测提示注入检测器

    提出 PIDS-Bench，评测提示注入检测器在过度防御与分布偏移下的表现

    arXiv
    2609.15017
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    TF-IDF + logistic regression, DistilBERT, DeBERTa-v3-FT and others7
    AbstractPIDS-Bench 显示高分布内 F1 仍会过度拦截外部来源的安全相关良性输入。

    PIDS-Bench 是一个冻结的检测器级基准，用来在固定阈值下同时看提示注入检测和良性误报。

    Paper analysisRead analysis
  6. Evaluation and benchmarksarXiv 2609.03221

    FairMedAgent：临床 LLM 智能体公平性审计中的随机噪声下限

    用 FairMedAgent 测量临床智能体在输入不变时的动作不稳定性下限

    arXiv
    2609.03221
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    claude-haiku-4-5, claude-sonnet-5, llama3.1:8b-instruct and others7
    Abstract先测同一输入下的动作不一致率，再用它解读人口学翻转率。

    FairMedAgent 把临床智能体公平审计里的采样噪声单独量出来：输入不变时动作仍会改变，这个比率就是解读翻转率的下限。。

    Paper analysisRead analysis
You have reached the end