Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter4

Model risks

Deception and scheming1Reward hacking4Dangerous agent actions4

System type

Models and APIs5AI Agent1coding agent0

Layer

Model layer5Application layer32Training and data layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Model risks：Deception and schemingSystem type：AI AgentSystem type：coding agentLayer：Training and data layerClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Risky behaviorarXiv 2604.28182

    研究提出探索作弊：LLM 可学会抵抗 RL 训练

    证明模型可在 RL 训练中少探索以抵抗能力诱发

    arXiv
    2604.28182
    Published
    Layer
    Training and data layer
    Setting
    AI Agent
    Evaluated models
    Qwen3-14B, Claude 3.7 Sonnet, Claude Sonnet 4 and others12
    Abstract锁定后的模型能选择性抵抗 RL 诱发。

    作者研究的是探索黑客：模型在 RL 中故意改变自己采样的轨迹，使训练结果偏离开发者想要的策略区。问题来自 on-policy RL 必须靠模型自己探索。若高奖励轨迹几乎不被采样，GRPO 的组内优势会消失。

    Paper analysisRead analysis
You have reached the end