Skip to content

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

Oct 13 · Tuesday

All papers

Found 4 papers
Filter4

Model risks

Deception and scheming19Reward hacking14Misalignment and value divergence11Dangerous agent actions24Dangerous capabilities9Hallucination and fabrication4

System type

LLM applications6AI Agent10coding agent2Multi-agent systems2

Layer

Application layer4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
Model risks：Hallucination and fabricationSystem type：coding agentSystem type：Multi-agent systemsLayer：Application layerClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. OtherarXiv 2609.12039

    现实才是最终验证者：智能体软件工程的两大关键缺口

    提出双缺口框架，统一智能体软件工程中的奖励投机与幻觉

    arXiv
    2609.12039
    Published
    Layer
    Application layer
    Setting
    coding agent
    Abstract双缺口解释内环为何会放行部署后不可接受的实现，外环用现实证据持续修订 R、M 与 E。

    Reality Is the Final Verifier 用 two-gap framework 解释智能体软件工程的主要失败，并主张用外层保证环持续收窄缺口，而不是试图在部署前证明缺口已关闭。

    Paper analysisRead analysis
  2. AttacksarXiv 2607.12340

    Research: LLM agent skill-name hallucination rates reach up to 62%, which can be exploited via squatting for supply-chain attacks

    提出技能名称抢注攻击，利用 Agent 虚构技能名实施供应链劫持

    arXiv
    2607.12340
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GLM-4.5-Air, GPT-5.4-mini, Claude Sonnet 4.6 and others12
    Abstract研究证实智能体虚构技能名具有高发生率与可预测性，现有防御难以兼顾安全与效用，亟需注册表结构性防护。

    本研究系统揭示了大模型智能体技能推荐场景下的虚构技能名称安全风险，将其形式化为一种新型供应链抢注攻击。

    Paper analysisRead analysis
  3. 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
  4. DefensesarXiv 2603.04474

    From Spark to Wildfire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration

    Proposing a lineage-graph governance layer to suppress error cascades in multi-agent collaboration

    arXiv
    2603.04474
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    AbstractA single seed can solidify into a false consensus along a fixed collaboration graph.

    The authors turn "small errors becoming collective false consensus" in LLM-MAS into a measurable propagation on a graph, and use a plug-in that only changes messages, not topology, to reduce the final infection.

    Paper analysisRead analysis
You have reached the end