Skip to content

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

Oct 13 · Tuesday

All papers

Found 172 papers
Filter6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.

Another 201papers do not have category tags yet and are not included in filtered results.

  1. OtherarXiv 2610.12756

    How hardware bit flips affect LLM agents: safety and alignment behavior can vary

    Measuring the impact of random weight bit flips on LLM agent safety and alignment behavior

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen3.6-27B, Qwen3.8-27B, Granite4.1-30B
    AbstractTwo-bit weight faults can be partially repaired in closed-loop settings, but they increase output tokens and, in specific models and scenarios, change safety or alignment behavior.

    After random two-bit weight faults enter an LLM agent, model-level damage becomes recoverable, increased cost, subtle semantic errors, and changes in safety or alignment behavior.

    Paper analysisRead analysis
  2. The paper proposes the ISE framework to evaluate LLM agents' epistemic humility under knowledge conflicts

    Proposes the ISE framework to evaluate the epistemic humility of LLM agents under knowledge conflicts

    Published
    Setting
    AI Agent
    Evaluated models
    Nemotron-Orchestrator-8B, Claude Sonnet 4.6, GPT-5 and others5
    AbstractISE trajectory evaluations show that high task accuracy across four agents does not correspond to higher cognitive humility.

    What the authors want to test is not whether the agent's final answer is correct, but whether, when a knowledge conflict arises, it recognizes the gap in its trajectory, performs bounded tool follow-up, and writes the unresolved uncertainty to the user.

    Paper analysisRead analysis
  3. One More Skill Installed: How Co-Installed Skills in Coding Agents Conflict

    评测编码 Agent 中相似技能共同安装对已装技能核心功能的替代

    Published
    Evaluated models
    claude-sonnet-4-6, claude-haiku-4-5-20251001, claude-opus-5 and others6
    Abstract冲突藏在任务成功后面。

    作者对共同安装、做同一件事的良性 skill 做实证研究,用核心功能是否还在,而不是任务过不过,来看冲突。。

    Paper analysisRead analysis
  4. SSCBench:评估工具调用 LLM Agent 故障注入测试证据有效性的测量协议与基准

    提出 SSCBench,评测工具调用 Agent 故障注入测试的证据有效性

    Published
    Setting
    AI Agent
    Evaluated models
    deepseek-flash, deepseek-v4-pro, gpt-5.6-luna and others5
    Abstract解释采纳前应报告该次执行的证据条件,以及支撑该主张的观察总体。

    SSCBench 研究工具使用智能体的故障注入结果,在什么证据条件下可以被解释。

    Paper analysisRead analysis
  5. 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
  6. 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
  7. 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
  8. 研究审计 LLM 读取 Agent 日志的取证能力:答案正确但引用来源多为猜测

    评测 LLM 审计 Agent 日志时来源重建是否有证据支持

    Published
    Setting
    AI Agent
    Evaluated models
    gpt-5.6-luna, claude-sonnet-4-6, gpt-5.4-mini-2026-03-17 and others5
    Abstract保存执行范围的标识绑定,才能把猜中的引用和证据支持的引用分开。

    包级审计检查保存的智能体动作里,哪些来源结论能被交给分析者的记录支持。

    Paper analysisRead analysis
  9. 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

    Published
    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
  10. AttacksarXiv 2610.09264

    研究者提出 PackHallu:经规则文件提示注入对编码 Agent 发起包幻觉攻击

    提出 PackHallu,经规则文件提示注入诱导编码 Agent 换用攻击者指定包

    Published
    Evaluated models
    Qwen2.5-Coder-7B, Qwen3-Coder-30B, Devstral-Small-2-24B and others19
    AbstractPackHallu 诱导规则文件换包。

    PackHallu 研究一种针对编程智能体规则文件的提示注入:让智能体在本应使用合法依赖时,改导入攻击者指定并控制的包。

    Paper analysisRead analysis
  11. 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
  12. DefensesarXiv 2610.08668

    SBW:面向 LLM 智能体的语义行为水印方法

    提出 SBW,为 LLM Agent 轨迹做抗改写与伪造的语义行为水印

    Published
    Setting
    AI Agent
    Evaluated models
    Qwen2.5-3B-Instruct, LLaMA-3.2-3B, Qwen2.5-7B and others5
    AbstractSBW 在语义簇上做溯源水印,改写检测高于精确符号,链式重放仍开放。

    SBW 是免训练的智能体行为水印,把所有者标识放在离散动作选择上,而不是输出 token。

    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