PulseAugur
中
实时 10:43:21
English(EN) ProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift

新的ProbeID系统在注册表漂移中验证LLM代理工具身份

研究人员开发了ProbeID,一个旨在验证大型语言模型(LLM)代理所使用的工具身份的系统,特别是在工具注册表可能发生漂移的情况下。ProbeID通过将规范化响应与模式验证探针进行比较,并与受信任的准入参考进行比对来工作,在出现歧义时避免做出决定。这种方法确保工具的可观察行为与其受信任的描述一致,从而防止恶意替换。在MCP-IdentityDrift数据集上的测试中,ProbeID达到了0.956的hit@1准确率,显著优于基于描述的路由器,并证明了其对数值噪声和更高计算成本的鲁棒性。 AI

影响 通过确保LLM代理所使用的工具的完整性,增强了LLM代理的安全性和可靠性。

排序理由 研究论文,详细介绍了LLM代理的一种新验证方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

新的ProbeID系统在注册表漂移中验证LLM代理工具身份

本文如何被排名

Signal score
12 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
研究论文,详细介绍了LLM代理的一种新验证方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, safety
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

  1. arXiv cs.AI TIER_1 English(EN) · Guanxing Chen, Sining Zhang, Haohuai He, Qiujie Lv, Yu-An Huang, Zhi-An Huang ·

    ProbeID:在注册表漂移下验证LLM代理的MCP工具身份

    arXiv:2610.33633v1 Announce Type: cross Abstract: Agents select tools by copyable descriptions, which cannot establish which implementation runs. ProbeID compares canonicalized responses to schema-valid probes with a trusted admission reference and abstains on ambiguity, so a squ…