Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter2

Model risks

Deception and scheming11Reward hacking4Misalignment and value divergence8Dangerous agent actions5

Impact

Oversight failure3

System type

Models and APIs37AI Agent31coding agent13science agent5Multi-agent systems4Embodied systems and robotics3

Layer

Application layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 305papers have no tags yet and are not included in filtered results.
Model risks：Reward hackingSystem type：Multi-agent systemsClear all

Another 305papers do not have category tags yet and are not included in filtered results.

  1. Risky behaviorarXiv 2610.12822

    Reward hacking as a transmissible strategy in multi-agent coding systems

    Show that reward hacking can propagate through code, memory, and plans in multi-agent coding systems

    arXiv
    2610.12822
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Evaluated models
    Qwen2.5-Coder-14B, Gemma-3-12B, Qwen2.5-Coder-7B and others16
    AbstractThe authors state that reward hacking can spread across models and affect routing and aggregation, and that review can reduce delivery.

    Reward hacking induced by coding RL can leave the source agent and enter subsequent collaboration and system coordination.

    Paper analysisRead analysis
  4. Risky behaviorarXiv 2609.04170

    Google DeepMind 案例研究：100 个自主研究智能体中自发涌现的作弊与举报

    展示自主科研智能体集群自发涌现的规范投机作弊与举报反制

    arXiv
    2609.04170
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    Gemini 3.1 Pro

    Abstract论文报告了百个智能体在数学证明中自发作弊扩散与举报抵制的案例，提出借鉴公地治理原则构建自律机制。

    Paper analysisRead analysis
You have reached the end