Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 2 papers
Filter2

Defense type

Instruction–data separation1Permissions and approval1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Defense type：Instruction–data separationDefense type：Permissions and approvalTopic: Agent safetyClear all
  1. Analysis and theoryarXiv 2610.06191

    研究：工具型智能体判断结果无用却仍继续检索，强制整合步骤可纠正

    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
  2. Analysis and theoryarXiv 2610.04375

    Paper reveals that LLM agent tool calls are rewritten during execution paths, and proposes IntAct as a fix

    提出 IEC 与 IntAct，测量并修复 Agent 工具调用的路径篡改

    arXiv
    2610.04375
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    qwen3-coder-plus, Qwen2.5-Coder-32B, Qwen2.5-72B and others4

    Abstract论文界定工具调用在执行路径中的意图偏离问题，提出无执行归因协议与跳级修复，为智能体工程提供评测与设计准则。

    Paper analysisRead analysis
You have reached the end