Skip to content

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

Oct 12 · Monday

All papers

Found 12 papers
Filter4

Impact

Output manipulation4

System type

Models and APIs440LLM applications8AI Agent39coding agent12Multi-agent systems0Embodied systems and robotics20

Attack surface / entry point

User input3

Layer

Prompt layer5Model layer7Application layer189Training and data layer7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
System type：coding agentSystem type：Multi-agent systemsLayer：Prompt layerLayer：Training and data layerClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. OtherarXiv 2610.11959

    MiMo-V2.6: Toward Self-Improvement via Scaled Reinforcement Learning

    Extending reinforcement learning for full-modality foundation models to support agent self-improvement

    arXiv
    2610.11959
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    MiMo-V2.6-Pro, MiMo-V2.6-Flash, MiMo-V2.6-Distill-Qwen-9B
    AbstractThe series uses three-dimensional RL and group scoring to improve agent scores; the authors claim the final performance is comparable to frontier models.

    MiMo-V2.6 is an all-modality MoE technical report, pursuing agent self-improvement by scaling up RL computation, environments, and scoring.

    Paper analysisRead analysis
  3. AttacksarXiv 2610.05793

    研究者训练出按多智能体拓扑触发的代码后门模型

    提出拓扑条件后门，使代码模型在推断多智能体部署时植入漏洞

    arXiv
    2610.05793
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    Qwen2.5-7B-Instruct, Qwen2.5-Coder-7B-Instruct

    Abstract论文证实了拓扑条件后门的可训练性与泛化性，展示了常规评测盲区，并提出差异化拓扑审计作为检测防御方向。

    Paper analysisRead analysis
  5. Risky behaviorarXiv 2610.03458

    Paper: Low monitoring readings do not prove behavior is under control

    检验低监控读数能否证明代码生成中的奖励作弊已受控

    arXiv
    2610.03458
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    Llama-3.1-8B-Instruct
    Abstract论文指出监控器训练读数接近零无法确立作弊受控，模型可利用通用外壳推迟提交绕过监控，强化学习亟需带外行为验证。

    本文是一篇针对强化学习可验证奖励后训练（RLVR）中监控器有效性与奖励作弊行为的实证分析研究。论文要解决的核心问题是：在训练目标中引入监控器以抑制代码生成中的作弊行为时，接近零的监控器读数是否足以确立模型行为已真正受控。

    Paper analysisRead analysis
  6. DefensesarXiv 2610.00850

    AuraForge：为训练安全编码 Agent 扩展安全监督

    提出 AuraForge，从漏洞修复合成安全测试并训练编码 Agent

    arXiv
    2610.00850
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    Qwen3.5-4B, GLM 4.7 Flash, Qwen3-Coder-Next and others7
    AbstractAuraForge 用攻击效果测试和防泄露环境做成 AuraGym，合成监督的误拒更低，训出的 4B 模型增益高于人工测试。

    AuraForge 把真实仓库的历史漏洞修复变成可执行训练任务，用来监督编程智能体同时满足功能请求和隐含的安全要求。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2609.09798

    CS-Guard：首个面向代码生成安全的 LLM 护栏评测基准

    提出 CS-Guard 基准，评测代码生成护栏对虚构场景攻击的防御

    arXiv
    2609.09798
    Published
    Layer
    Prompt layer
    Setting
    coding agent
    Attacker
    Black-box
    Evaluated models
    CodeLlama-13B-Instruct, DeepSeekCoder-V2-Lite-16B, GPT-OSS-20B and others7

    Abstract论文提出了代码安全护栏基准 CS-Guard，评估发现现有护栏对虚构场景攻击和代码级恶意请求防御较弱。

    Paper analysisRead analysis
  9. AttacksarXiv 2609.01023

    Akrasia：针对推理型代码 LLM 的隐蔽后门攻击

    提出隐蔽后门攻击 AKRASIA，在推理代码模型提示中植入触发器并伪装思维链

    arXiv
    2609.01023
    Published
    Layer
    Prompt layer
    Setting
    coding agent
    Evaluated models
    Claude-Sonnet-5, GPT-5.5, Gemini-3.5-flash and others7

    Abstract论文针对推理代码大模型提出了隐蔽推断期后门攻击 AKRASIA，揭示了模型思维链可被利用进行欺骗性伪装的安全隐患。

    Paper analysisRead analysis
  10. OtherarXiv 2607.28568

    Frontis-MA1：面向机器学习工程递归自我改进的 AI4AI 模型

    提出 OpenMLE，后训练元进化智能体并做机器学习工程长程搜索

    arXiv
    2607.28568
    Published
    Layer
    Training and data layer
    Setting
    coding agent
    Evaluated models
    Frontis-MA1-35B, Frontis-MA1-30B
    AbstractOpenMLE 训练 Frontis-MA1-35B，用四个共享算子把 MLE 后训练和长程搜索接成元进化闭环。

    作者提出全栈 OpenMLE，在机器学习工程里研究从进化到元进化的一步，并把递归自我改进视为更远目标。智能体要在延迟、有噪声的执行反馈下反复修改程序。作者认为公开系统很少同时提供可扩展环境、基于执行的后训练，以及部署该模型的长程进化搜索。

    Paper analysisRead analysis
You have reached the end