Skip to content

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

Oct 13 · Tuesday

Agent safety · Papers

Found 6 papers
Filter4

Model risks

Dangerous agent actions3

Impact

Unauthorized actions88Data and privacy leaks16Output manipulation15Availability and reliability6Oversight failure8

System type

AI Agent6Browser and computer use0Multi-agent systems0

Layer

Application layer6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Impact：Availability and reliabilitySystem type：AI AgentSystem type：Browser and computer useSystem type：Multi-agent systemsTopic: Agent safetyClear all
  1. Evaluation and benchmarksarXiv 2610.11647

    One More Skill Installed: How Co-Installed Skills in Coding Agents Conflict

    评测编码 Agent 中相似技能共同安装对已装技能核心功能的替代

    arXiv
    2610.11647
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    claude-sonnet-4-6, claude-haiku-4-5-20251001, claude-opus-5 and others6
    Abstract冲突藏在任务成功后面。

    作者对共同安装、做同一件事的良性 skill 做实证研究，用核心功能是否还在，而不是任务过不过，来看冲突。。

    Paper analysisRead analysis
  2. DefensesarXiv 2610.10833

    研究：Agent 准时停机不等于有效使用时间预算

    用时钟 harness 和预算塑形 GRPO 改善 Agent 的按时返回

    arXiv
    2610.10833
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen3.6-27B, Qwen3-4B, Qwen3.5-9B and others4
    Abstract作者比较提示词、harness 与 GRPO：按时性可改善，但额外时间仍未变成更好解。

    作者研究小规模 LLM 智能体在显式 wall-clock 预算下能否按时返回，并把更多时间换成更好的解。

    Paper analysisRead analysis
  3. Analysis and theoryarXiv 2610.06191

    Research: tool-based agents continue searching even after judging results useless; forced integration steps can correct this

    揭示工具型智能体判定无用后仍不停止检索，并检验强制整合纠正效果

    arXiv
    2610.06191
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Qwen2.5-7B, Llama-3.1-8B, Qwen3-8B and others7
    Abstract论文揭示智能体判定工具失效却无法转化为停止行动，证实通过框架规则强制整合判定可提升表现。

    本文针对智能体在工具静默失效时过度检索的问题，系统分析了判定、信念与停止行动之间的解耦现象，并提出了外部规则整合方案。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2609.33658

    AgentBound：面向工具型 LLM Agent 安全的四路反事实评测框架

    提出 AGENT BOUNDARY，用四向反事实任务评测工具智能体行动边界

    arXiv
    2609.33658
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.5, Claude Opus 4.8, Gemini 3.5 Flash and others15
    Abstract四向反事实基准把过度拒绝和未授权遵从拆开，Thought 校正在十个配置上提高已授权完成。

    AGENT BOUNDARY 是面向工具使用 LLM 智能体的四向可执行反事实评测，并附带一个决策时 Thought 校准模块。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 2605.19722

    研究用 30 项漏洞分析任务评测自主安全智能体的安全对齐效果

    评测自主安全智能体在授权漏洞分析中的对齐拒答效应

    arXiv
    2605.19722
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    Gemma 4 31B official instruction-tuned model, TrevorJS Gemma 4 31B uncensored GGUF, Gemma 4 26B A4B official instruction-tuned model and others8
    Abstract轨迹级评测把拒答、接地、工具接口分开。

    这项工作把安全对齐效应测成自主安全智能体的轨迹属性，而不是单轮拒答率。

    Paper analysisRead analysis
  6. AttacksarXiv 2602.07379

    Aegis: Governance, Integrity, and Security for AI Voice Agents

    Proposes the Aegis red-teaming framework for multi-turn attacks on high-risk voice agents.

    arXiv
    2602.07379
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-4o, GPT-4o-mini, Gemini-1.5 Pro and others7
    AbstractAegis red-teams three types of voice agents: query-based access eliminates authentication and leakage successes, but behavioral attacks remain.

    Aegis uses multi-turn red-teaming evaluation on ALLM voice agents already integrated into business systems. The authors call this the first systematic red-teaming framework in this setting.

    Paper analysisRead analysis
You have reached the end