Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter3

Attack surface / entry point

User input7Tool responses3Tool and skill descriptions4Code repositories and dependencies2Retrieval corpus6Inter-agent messages3

System component

Guardrails and judges3Permissions and sandboxing2Embeddings0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Attack surface / entry point：Code repositories and dependenciesSystem component：Permissions and sandboxingSystem component：EmbeddingsClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  2. AttacksarXiv 2605.12673

    UC Berkeley proposes BenchJack, which automatically audits 10 agent benchmarks and finds 219 reward hacking defects.

    提出 BENCHJACK，审计 Agent 基准中的奖励作弊缺陷

    arXiv
    2605.12673
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Abstract论文系统揭示了智能体基准的奖励作弊隐患，提出自动化红队审计与迭代修补系统 BENCHJACK。

    论文系统研究了主流 AI 智能体基准评测中的奖励作弊问题，提出了首个针对基准缺陷的自动化红队审计与生成对抗式迭代修补系统 BENCHJACK。

    Paper analysisRead analysis
You have reached the end