Skip to content

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

Oct 12 · Monday

All papers

Found 268 papers
Filter4
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.

Another 247papers do not have category tags yet and are not included in filtered results.

  1. DistressBench: Evaluating multi-dimensional crisis support in large language models

    Introduces DistressBench, evaluating models' multidimensional support in crisis conversations

    Published
    Evaluated models
    Muse Spark 1.2, Muse Spark 1.3, Muse Glimmer 30B and others20
    AbstractThe model is more restrained and acts less.

    DistressBench uses SSH dialogues written and revised by clinical personnel, and evaluates how much necessary care general chat models deliver according to weighted atomic criteria, rather than whether they refuse. When users disclose suicidal ideation or self-harm to a chat model, the authors consider the expected behavior to be recognizing the crisis, calibrating empathy, de-escalating, and referring to human help. Refusal-based evaluations cannot detect failing to act after recognizing the crisis.

    Paper analysisRead analysis
  2. AttacksarXiv 2610.12292

    The paper proposes an option channel attack: changing one option label can make an agent guardrail allow a prohibited operation

    Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations

    Published
    Attacker
    Black-box
    Evaluated models
    LAYA-TD, LAYA-EN, LAYA-ML and others5

    AbstractThe authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.

    Paper analysisRead analysis
  3. DefensesarXiv 2610.10833

    研究:Agent 准时停机不等于有效使用时间预算

    用时钟 harness 和预算塑形 GRPO 改善 Agent 的按时返回

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen3.6-27B, Qwen3-4B, Qwen3.5-9B and others4
    Abstract作者比较提示词、harness 与 GRPO:按时性可改善,但额外时间仍未变成更好解。

    作者研究小规模 LLM 智能体在显式 wall-clock 预算下能否按时返回,并把更多时间换成更好的解。

    Paper analysisRead analysis
  4. PatchBench 提出激活补丁局部评测协议,揭示越狱修复的附带损伤

    提出 PatchBench-Local 协议,评测激活补丁修复越狱的局部附带损伤

    Published
    Evaluated models
    Qwen2.5-3B-Instruct, Qwen2.5-14B-Instruct, gemma-3-4b-it and others8

    Abstract论文提出 PatchBench 与局部评估协议,揭示了激活补丁在全局能力无损下仍存局部良性退化。

    Paper analysisRead analysis
  5. 研究:Agent 更依赖工具报错通道

    测量工具调用 Agent 对显式报错与静默损坏的检测和恢复

    Published
    Setting
    AI Agent
    Evaluated models
    claude-haiku-4.5-thinking, claude-haiku-4.5, deepseek-r1 and others6
    Abstract作者称智能体看错误通道而非返回内容,静默损坏更少被当作问题。

    作者在 BFCL 多轮可执行环境上注入一次工具层故障,把注意到、改计划、恢复和重复分开记分,而不是只看任务有没有做完。

    Paper analysisRead analysis
  6. AgentTime 基准测试智能体时长遵循能力,GPT-6 Astra 出现 14 次做完后休眠

    提出 AgentTime 基准,评测智能体按时长工作与估时能力

    Published
    Evaluated models
    Fable 5.1, GPT-5.6 Sol, GPT-6 Astra and others7
    Abstract作者把完成任务和管理所用时间分开。

    AgentTime 是对智能体时间自控的评测:预测任务耗时、按要求时长工作、事后估计已用时间。

    Paper analysisRead analysis
  7. DefensesarXiv 2610.09793

    用时序逻辑监控工具 Agent

    提出 MFOTL 离线时序验证以监控工具 Agent 的危险动作链

    Published
    Setting
    AI Agent
    Attacker
    Black-box
    Abstract形式化验证可有效识别多步攻击,但其有效性高度依赖轨迹的可信历史记录。

    这篇论文对工具调用大语言模型智能体的安全监控进行了形式化时序验证研究。

    Paper analysisRead analysis
  8. AttacksarXiv 2610.10612

    PyCache Trap 利用 Python 缓存替换绕过七款 Agent Skill 扫描器

    提出 PyCache Trap,用字节码缓存替换绕过 Agent 技能扫描器

    Published
    Evaluated models
    CISCO, HSS, AUDITOR and others8
    Abstract论文剖析智能体技能审查与执行脱节盲区,提出 PyCache Trap 攻击并构建基于可信复现的 EAV 防御。

    这篇论文研究了智能体技能(Agent Skills)安全扫描中的“审查–执行脱节”问题,并提出了对应的攻击验证与防御方案。

    Paper analysisRead analysis
  9. 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

    Published
    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
  10. 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

    Published
    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
  11. AttacksarXiv 2610.08951

    ASPIRE:面向 LLM Agent 的开放式提示注入红队引擎

    提出 ASPIRE 行为图搜索,开放式发现 Agent 提示注入漏洞

    Published
    Setting
    AI Agent
    Evaluated models
    Gemini-3.7-Flash, DeepSeek-V4-Flash, Gemini-2.5-flash
    AbstractASPIRE 把提示注入红队从载荷优化改成行为图引导的开放式漏洞发现。

    ASPIRE 是给搭建方用的智能体提示注入红队引擎,目标是开放式画出可利用的行为路径,而不是在固定任务上打磨一条载荷。

    Paper analysisRead analysis
  12. OtherarXiv 2610.08917

    CARE:为视觉-语言-动作模型推理加速提供认证式选择

    提出 CARE,离线认证 VLA 加速配置的回合级失败风险并选出最快合格候选

    Published
    Evaluated models
    OpenVLA-OFT, π0.5, π0 and others5
    AbstractCARE 以配对回合认证加速诱发失败,在预算内选最快候选,不足则保留参考。

    CARE 在部署前从加速配置中选出最快、且加速诱发失败风险能被有限样本认证为低于用户预算的候选。证据不足就保留全计算参考策略。

    Paper analysisRead analysis
  13. ParanoiaEval:编码智能体不必要风险处置评测基准发布

    提出 ParanoiaEval 评测编码智能体的不必要风险处置

    Published
    Evaluated models
    Opus-5, Sonnet-5, Sonnet-4.6 and others8
    Abstract作者用证据受控任务对评测风险处置,称其普遍、独立于任务能力并降低满意度。

    作者提出 ParanoiaEval,并称它是编码智能体风险处置能力的首个统一基准。要解决的问题是:证据已经确定风险应如何处置之后,智能体仍可能扩大验证、增加保护或备份,而现有评测要么只看功能正确性,要么把相关行为拆开研究。做法是把 NIST 的 ATMA 落到仓库任务。

    Paper analysisRead analysis
  14. DefensesarXiv 2610.08082

    POLAR:面向小型工具调用智能体的可逆性护栏框架

    提出 POLAR 本体门控,在执行前否决不可逆工具调用

    Published
    Setting
    AI Agent
    Evaluated models
    qwen/qwen3-8b, meta-llama/llama-3.1-8b-instruct, nvidia/nemotron-nano-9b-v2 and others6
    Abstract训练无关的事前可逆性门控,弱 airline 模型有收益,强模型与 retail 常回落。

    POLAR 是训练无关的事前门控,用类型化本体在工具调用执行前检查能否组成候选逆序列。

    Paper analysisRead analysis