Skip to content

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

Oct 12 · Monday

All papers

Found 7 papers
Filter4

Defense type

Detection and filtering3

Impact

Unauthorized actions4

System type

Models and APIs89LLM applications50AI Agent50coding agent8science agent4web agent4Multi-agent systems5Embodied systems and robotics3

Layer

Application layer4

System component

RAG3Guardrails and judges7Monitors3Permissions and sandboxing3Vision18Embeddings0Multimodal20
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.
System type：web agentSystem type：Embodied systems and roboticsSystem component：Guardrails and judgesSystem component：EmbeddingsClear all

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

  1. DefensesarXiv 2610.08761

    VeriFine：通过扩展验证实现具身推理的自我改进

    提出 VeriFine，用双环协同扩展验证以实现具身推理自我改进

    arXiv
    2610.08761
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    Alpamayo 1.5 8B, Qwen3-VL 2B, Claude Opus 5
    AbstractVeriFine 用双环协同演化具身推理的策略、课程和评审，驾驶与导航的策略分和评审对齐都上升。

    VeriFine 把驾驶和导航推理的自改进写成策略、课程和无参考评审的协同演化，用来处理固定评审跟不上新失败模式的问题。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2604.06240

    研究者开源 Universal Verifier 与 CUAVerifierBench，用于验证计算机使用 Agent 轨迹

    构建 Universal Verifier 核验计算机使用 Agent 轨迹

    arXiv
    2604.06240
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5.2, GPT-4o, o4-mini and others8
    Abstract四条设计原则叠成 Universal Verifier，作者称其与人类一致程度相当且假阳性近零。

    Universal Verifier 给计算机使用轨迹打过程分和结果分，并定位失败。CUAVerifierBench 用人工标签衡量这种验证器。

    Paper analysisRead analysis
  4. AttacksarXiv 2604.03890

    From prompts to physical actions: structured backdoor attacks against LLM-mediated robot control systems

    Propose a structured JSON backdoor that triggers malicious actions in robot control via a poisoned LoRA

    arXiv
    2604.03890
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics, LLM applications
    Evaluated models
    Llama-3.1-8B-Instruct, Gemma-2-9B-IT, DeepSeek-R1-Distill-Llama-8B and others4

    Abstract推理层后门传不到执行。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2510.01354

    WAInjectBench 系统评测网页 Agent 的提示注入检测方法

    提出 WAInjectBench 评测网页 Agent 的提示注入检测

    arXiv
    2510.01354
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-4o, Mistral-7B-Instruct-v0.1, Llama-Prompt-Guard-2-86M and others8
    AbstractWAInjectBench 比较网页智能体的提示注入检测：显式线索可被部分检出，隐蔽攻击大多漏检。

    WAInjectBench 是网页智能体提示注入检测的基准。作者要看现有检测器能否发现这类攻击：攻击者改网页，使智能体执行目标动作，而不是用户任务。作者称这是首个此类综合基准。

    Paper analysisRead analysis
You have reached the end