Skip to content

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

Oct 13 · Tuesday

All papers

Found 132 papers
Filter4

Attack type

Jailbreaks6Prompt injection51Poisoning and backdoors12Extraction and theft3Malicious use3

Attack technique

Gradient and representation optimization7Automated search5Cross-modal payloads5Dormant triggers4

Model risks

Deception and scheming11Reward hacking4Misalignment and value divergence9Dangerous agent actions12Inappropriate refusal3

Defense type

Detection and filtering8Instruction–data separation10Permissions and approval12Monitoring and auditing3

Impact

Harmful content10Unauthorized actions34Data and privacy leaks14Output manipulation32Availability and reliability7Oversight failure10

System type

Models and APIs9LLM applications130AI Agent605coding agent121science agent30web agent34Browser and computer use18Multi-agent systems82Embodied systems and robotics17

Attack surface / entry point

User input18Web pages and interfaces25Documents and messages11Tool responses10Tool and skill descriptions4Retrieval corpus4Memory writes8Inter-agent messages25Images, audio and video5

Layer

Prompt layer6Model layer11Application layer132Training and data layer14

System component

MCP and skills5Memory14RAG4Guardrails and judges9Monitors9Permissions and sandboxing15Vision10Multimodal10
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.
System type：web agentSystem type：Multi-agent systemsSystem type：Embodied systems and roboticsLayer：Application layerClear all

Another 213papers 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
  6. 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
  7. 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. 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
  10. 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
  12. 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
  16. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击

    arXiv
    2610.07657
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
  17. Evaluation and benchmarksarXiv 2610.06748

    BazaarBench：评估 LLM Agent 在去中心化 C2C 市场中的代理安全

    构建 BazaarBench，评测 C2C 市场中 Agent 的违规与失信行为

    arXiv
    2610.06748
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.5, GPT-5.4, GPT-5.4-mini and others5
    Abstract论文提出挂钩底层资产的 C2C 交易评测基准，发现时间压力与对抗指令显著推高了智能体的违规承诺与欺诈行为。

    BazaarBench 针对大语言模型智能体在去中心化 C2C 交易中的代理安全问题，提出了一个结合底层实体状态与大模型裁判的仿真基准平台。

    Paper analysisRead analysis
  19. DefensesarXiv 2610.05640

    Research reveals that the CaMeL defense fails in multi-agent systems and proposes multi-CaMeL

    提出 multi-CaMeL，在智能体调用边界隔离可信指令与非可信数据

    arXiv
    2610.05640
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Claude Fable 5, GPT-5.5, GPT-4.1 and others6

    Abstract论文针对多智能体中单体防御不组合的边界清洗问题，提出 multi-CaMeL 协议彻底阻断了 MultiAgentDojo 上的注入攻击。

    Paper analysisRead analysis
  20. Evaluation and benchmarksarXiv 2610.05586

    AgentDoxx：联网搜索 Agent 对匿名访谈文本的再识别评测

    构建 AGENTDOXX 基准，评测联网搜索 Agent 对匿名访谈的再识别

    arXiv
    2610.05586
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5.6 Terra, GPT-5 Mini, GPT-4.1 Mini and others10

    Abstract论文提出了已知身份的重识别基准 AGENTDOXX，揭示搜索与记忆双重风险及现有防御在检索轨迹中的泄露漏洞。

    Paper analysisRead analysis
Load more