Skip to content

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

Oct 13 · Tuesday

All papers

Found 187 papers
Filter4

Attack type

Jailbreaks6Prompt injection51Poisoning and backdoors17Extraction and theft3Malicious use4

Attack technique

Gradient and representation optimization12Automated search7Cross-modal payloads7Dormant triggers8

Model risks

Deception and scheming15Reward hacking10Misalignment and value divergence10Dangerous agent actions18Dangerous capabilities9Inappropriate refusal5Hallucination and fabrication5

Defense type

Model hardening9Inference-time intervention4Detection and filtering8Instruction–data separation12Permissions and approval14Monitoring and auditing5

Impact

Harmful content13Unauthorized actions43Data and privacy leaks13Output manipulation43Availability and reliability18Oversight failure14

System type

Models and APIs888LLM applications146AI Agent669coding agent140science agent32web agent34Browser and computer use19Multi-agent systems82Embodied systems and robotics47

Attack surface / entry point

User input22Web pages and interfaces25Documents and messages10Tool responses9Tool and skill descriptions4Retrieval corpus4Memory writes8Inter-agent messages25Images, audio and video12Training data5Weights and gradients3Distribution channels4

Layer

Prompt layer6Model layer11Application layer154Training and data layer16

System component

MCP and skills5Memory13RAG4Guardrails and judges14Monitors12Reasoning chains4Permissions and sandboxing17Fine-tuning and open weights3Vision18Multimodal20
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
System type：science agentSystem type：web agentSystem type：Multi-agent systemsSystem type：Embodied systems and roboticsClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.13710

    OpenSocialJax: Evaluating Social Adaptation in Sequential Social Dilemmas with Open-Ended Environment Dynamics

    Evaluating multi-agent adaptation in social dilemmas with hidden rules using OpenSocialJax

    arXiv
    2610.13710
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-6-Luna, GPT-6-Sol, Claude Opus 5.5 and others8
    AbstractThe authors report that rule discovery often improves payoffs, but public good cleaning becomes concentrated, and shared resources are eventually depleted.

    OpenSocialJax evaluates whether LLMs can simultaneously adapt to unfamiliar environmental mechanisms and other agents in sequential social dilemmas.

    Paper analysisRead analysis
  2. OtherarXiv 2610.13491

    EviRepair: Evidence-Driven Agents for Reliable Vulnerability Repair

    Proposing EviRepair, an evidence-driven multi-agent framework for repository-level vulnerability repair

    arXiv
    2610.13491
    Published
    Layer
    Application layer
    Setting
    coding agent, Multi-agent systems
    Evaluated models
    DeepSeek-V4.1-Flash, GLM-5.2, Qwen3.8-27B
    AbstractEviRepair uses a reviewed vulnerability model for repository-level repair.

    EviRepair is a repository-level automated vulnerability repair framework for sparse vulnerability reports, using a reviewed vulnerability model to separate diagnosis from patch synthesis.

    Paper analysisRead analysis
  3. OtherarXiv 2610.13479

    A local agentic AI framework generates edge-case scenarios for safety assurance

    Proposes a local dual-model closed loop to generate edge scenarios for autonomous system safety assurance

    arXiv
    2610.13479
    Published
    Layer
    Application layer
    Setting
    LLM applications, Embodied systems and robotics
    Evaluated models
    PPO
    AbstractLocal closed-loop generation of JSON edge cases.

    The authors built a local agentic loop that runs on a laptop to generate edge cases for safety arguments of autonomous systems, rather than releasing a new public test set.

    Paper analysisRead analysis
  5. OtherarXiv 2610.13372

    Toward Safe World Models: Risks, Defenses, and Evaluation

    A survey of risks, defenses, and evaluation in the six-stage lifecycle of world models

    arXiv
    2610.13372
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    AbstractSafety is written as a property of the prediction-decision closed loop; claims must be linked to observed consequences and versions.

    World model safety is organized by the nature of the prediction-decision loop, not by isolated prediction scores.

    Paper analysisRead analysis
  7. 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
  8. Analysis and theoryarXiv 2610.12436

    The study proposes an ecological theory of AI agent populations: collaboration brings a critical scale for takeoff.

    An ecological model is established for a population of mismatched agents, showing that collaboration produces a critical takeoff scale.

    arXiv
    2610.12436
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    AbstractThe authors say that collaboration changes takeoff from an individual capability threshold to a population threshold, so small-population evaluations are insufficient.

    The authors use the ecological strong Allee effect to discuss whether a mismatched agent population can take off when individual capabilities remain unchanged..

    Paper analysisRead analysis
  9. DefensesarXiv 2610.12432

    FAITH: A feasibility-aware safety filtering reinforcement learning framework for high-dimensional systems

    Proposes the FAITH safe filtering reinforcement learning framework, training high-dimensional systems to optimize task reward under constraints

    arXiv
    2610.12432
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    AbstractFAITH separates safety filtering from reward optimization.

    FAITH is a model-free safe filtering reinforcement learning framework for high-dimensional systems: safety correction and task reward reside in separate modules.

    Paper analysisRead analysis
  11. DefensesarXiv 2610.11754

    仅凭输出审查无法验证什么：面向研究智能体的研究契约

    提出研究合同，把已批准选择绑定到执行证据并由检查器核验

    arXiv
    2610.11754
    Published
    Layer
    Application layer
    Setting
    science agent
    Evaluated models
    OpenAI gpt-5.6-sol, OpenAI gpt-5.6-terra, OpenAI gpt-5.6-luna and others18
    Abstract研究合同暴露四类输出单独建不立的关系。

    研究合同用来核验计算科学研究智能体是否仍在已批准研究之内，不判断科学是否为真。。

    Paper analysisRead analysis
  12. OtherarXiv 2610.11467

    GROB studies the attribution boundaries of autonomous agent activity using public web traces

    提出 GROB，用只读公开痕迹保存候选智能体线索并检验归因边界

    arXiv
    2610.11467
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract作者称 Census 是最强例。

    GROB 是一套多角色架构，在没有特权遥测、也不预先指定目标时，从公开网页痕迹里保存候选自主智能体活动，供日后解析。

    Paper analysisRead analysis
  14. OtherarXiv 2610.10064

    研究者提出理解审计机制，以缓解自动化 AI 研究带来的风险

    提出 comprehension audits，以人类理解证据作为继续研发门槛

    arXiv
    2610.10064
    Published
    Layer
    Training and data layer
    Setting
    science agent
    Abstract理解审计把出示人类理解设为继续研发的门禁，并报告开源评审评论率下降。

    本文是一份研发过程保障提案：用 comprehension audits 检验责任人是否理解 AI 参与产生的研发贡献，未达标就暂停后续开发与依赖该贡献的发布。。

    Paper analysisRead analysis
  16. Analysis and theoryarXiv 2610.09517

    审计发现 CLIP 安全分数主要反映画面与提示词场景的相似度

    开环审计冻结视觉语言安全分，发现其反映场景模板而非危险感知

    arXiv
    2610.09517
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    CLIP ViT-B/32, CLIP ViT-L/14, Qwen2-VL-7B
    Abstract论文审计了冻结 VLM 安全评分机制，指出其反映场景模板而非危险感知，为安全强化学习评估提供了严谨基准。

    本文是一项针对安全强化学习中冻结视觉语言模型（VLM）安全评分机制的实证审计研究。

    Paper analysisRead analysis
  17. DefensesarXiv 2610.09496

    SOUL：用稀疏特征策略遗忘缓解 VLA 模型的状态幻觉

    提出 SOUL 稀疏特征策略遗忘，缓解 VLA 状态幻觉

    arXiv
    2610.09496
    Published
    Layer
    Training and data layer
    Setting
    Embodied systems and robotics
    Evaluated models
    OpenVLA, π0.5
    AbstractSOUL 以稀疏特征遗忘 VLA 状态幻觉。

    SOUL用稀疏特征引导的策略 unlearning 处理 VLA 的 state hallucination。

    Paper analysisRead analysis
  18. DefensesarXiv 2610.09469

    Secure-CUA: Constraining the Impact of Untrusted Content in Computer-Use Agents

    提出 Secure-CUA，用动作事务约束计算机使用智能体的不可信影响

    arXiv
    2610.09469
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    Claude Opus 5, Gemini 3.8 Flash, GPT-5.6-Sol
    AbstractSecure-CUA 用每步事务约束不可信影响，良性 TSR 接近 Vanilla-CUA。

    Secure-CUA 要限制图形界面里不可信内容对 CUA 决策和 GUI 执行的影响，同时保留合法任务所需的不可信信息。

    Paper analysisRead analysis
  20. AttacksarXiv 2610.09240

    WebMirage hijacks visual web agents' browser operations with adversarial images

    提出 WebMirage，用局部对抗图像劫持视觉网页 Agent 的浏览器操作

    arXiv
    2610.09240
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    LLaVA-v1.5-13B, LLaVA-v1.6-34B, MiniCPM-o-8B and others6
    Abstract论文提出了针对网络智能体的端到端视觉红队框架 WebMirage，揭示了从视觉定位到浏览器执行的安全脆弱性。

    WebMirage 是一个面向视觉定位网络智能体的流水线感知端到端红队攻击框架。

    Paper analysisRead analysis
Load more