Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter2

Model risks

Deception and scheming12Reward hacking4Misalignment and value divergence8Dangerous agent actions5Hallucination and fabrication2

System type

Models and APIs24LLM applications7AI Agent13coding agent4Multi-agent systems2
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：Hallucination and fabricationSystem type：Multi-agent systemsClear all

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

  1. Evaluation and benchmarksarXiv 2606.18021

    LegalHalluLens：面向法律 AI 的分类幻觉审计与校准多智能体辩论

    提出 LegalHalluLens，分类审计法律抽取幻觉并校准多智能体辩论

    arXiv
    2606.18021
    Published
    Layer
    Application layer
    Setting
    LLM applications, Multi-agent systems
    Evaluated models
    gemini-3-flash, gpt-5.2, qwen3-32b and others5
    Abstract作者称类型画像与 RDI 能区分聚合率相近的系统，辩论主要减少虚构检出。

    LegalHalluLens 是一套法律条款抽取的审计框架，外加一个按审计结果校准的辩论缓解。。

    Paper analysisRead analysis
  2. DefensesarXiv 2603.04474

    从火花到烈火：建模并缓解基于 LLM 的多智能体协作中的错误级联

    提出谱系图治理层抑制多智能体协作的错误级联

    arXiv
    2603.04474
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract单一种子可沿固定协作图固化为错误共识。

    作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播，并用只改消息、不改拓扑的插件压低最终感染。

    Paper analysisRead analysis
You have reached the end