Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Model risks

Dangerous agent actions1

Defense type

Instruction–data separation1

Impact

Output manipulation1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Model risks：Dangerous agent actionsDefense type：Instruction–data separationImpact：Output manipulationClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2609.32520

    IntentFlux 基准测量 LLM Agent 的意图漂移并给出 StateForge 修复方案

    提出 IntentFlux 测量 Agent 意图漂移并提出 StateForge 修复

    arXiv
    2609.32520
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude Opus 4.7, DeepSeek V4 Pro, Gemini 3.5 Flash and others9
    AbstractINTENTFLUX 量化意图漂移，STATEFORGE 用显式状态部分缩小差距，但未回到单轮水平。

    这篇工作把“用户改口后，过时意图仍影响答案或工具动作”做成可评分的多轮失败，并试验在生成前显式维护活跃状态。

    Paper analysisRead analysis
You have reached the end