Skip to content

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

Oct 13 · Tuesday

All papers

Found 7 papers
Filter5

Attack type

Prompt injection3

Model risks

Deception and scheming11Reward hacking16Misalignment and value divergence3Dangerous agent actions19Dangerous capabilities16Inappropriate refusal3Hallucination and fabrication4

Impact

Unauthorized actions4

System type

LLM applications8AI Agent30coding agent5science agent3Multi-agent systems11

Layer

Application layer7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Model risks：Misalignment and value divergenceModel risks：Hallucination and fabricationSystem type：coding agentSystem type：science agentLayer：Application layerClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.32616

    Cave-Bench：虚假指控下 LLM 智能体最高 60.06% 的运行会破坏正确工作

    提出 CAVE-BENCH，评测智能体在虚假指责下破坏已完成的正确工作

    arXiv
    2609.32616
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Claude-Sonnet-5, Claude-Opus-5, GPT-5.6-Sol and others14

    Abstract论文提出了评估智能体在虚假指责下破坏已有正确成果的 CAVE-BENCH，发现强模型易推翻已知证据，提出了门控缓解方案。

    Paper analysisRead analysis
  2. DefensesarXiv 2609.24165

    APEXA 为同步辐射数据处理的 LLM 多智能体加装执行完整性护栏

    提出 APEXA，在工具层拒绝无执行支撑的结果并拦截电机命令

    arXiv
    2609.24165
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    GPT-5-mini, GPT-5.4, Claude Opus 4.7 and others4
    Abstract作者称执行是否发生要由工具层核对，而不能只靠提示词。

    APEXA 是先进光子源上的数据还原框架，用工具层代码约束语言模型智能体的工具调用。

    Paper analysisRead analysis
  3. OtherarXiv 2609.12039

    现实才是最终验证者：智能体软件工程的两大关键缺口

    提出双缺口框架，统一智能体软件工程中的奖励投机与幻觉

    arXiv
    2609.12039
    Published
    Layer
    Application layer
    Setting
    coding agent
    Abstract双缺口解释内环为何会放行部署后不可接受的实现，外环用现实证据持续修订 R、M 与 E。

    Reality Is the Final Verifier 用 two-gap framework 解释智能体软件工程的主要失败，并主张用外层保证环持续收窄缺口，而不是试图在部署前证明缺口已关闭。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2608.00711

    SCHEMA：面向科学 Agent 幻觉的拓扑感知评测框架

    提出 SCHEMA，用概念图与轨迹分评测科学 Agent 幻觉

    arXiv
    2608.00711
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    Kimi-K2.5, Qwen3.6-Plus, Llama-4-Scout and others10
    AbstractSCHEMA 用知识拓扑评估科学智能体幻觉，终答正确仍可能来自有缺陷的中间推理。

    SCHEMA 是面向科学智能体幻觉的证据锚定评测框架，实例化在生物医学的 Protein Domain 与 PathVQA-Enhanced。作者在摘要中称它是首个同时做到证据锚定和拓扑感知的此类框架。

    Paper analysisRead analysis
  6. AttacksarXiv 2607.12340

    Research: LLM agent skill-name hallucination rates reach up to 62%, which can be exploited via squatting for supply-chain attacks

    提出技能名称抢注攻击，利用 Agent 虚构技能名实施供应链劫持

    arXiv
    2607.12340
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GLM-4.5-Air, GPT-5.4-mini, Claude Sonnet 4.6 and others12
    Abstract研究证实智能体虚构技能名具有高发生率与可预测性，现有防御难以兼顾安全与效用，亟需注册表结构性防护。

    本研究系统揭示了大模型智能体技能推荐场景下的虚构技能名称安全风险，将其形式化为一种新型供应链抢注攻击。

    Paper analysisRead analysis
You have reached the end