English(EN) Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy

新框架TG-CI增强了多智能体LLM系统的隐私性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-31 04:00

研究人员推出了一种名为任务图上下文完整性（TG-CI）的新型框架，旨在增强多智能体大型语言模型（LLM）系统的隐私性。与孤立评估披露的现有方法不同，TG-CI通过将整个工作流程形式化为多智能体任务图（MATG）来规范隐私。这种方法评估信息在计划的操作序列中的流动，确保披露不仅在传输点是恰当的，而且还考虑了信息如何传播给下游智能体。使用新的MAPLE-Bench基准进行的实验表明，TG-CI在保持高任务准确性的同时显著减少了未经授权的披露，并在隐私、成本和效用之间提供了互补的权衡。 AI

影响通过考虑信息传播，增强了复杂多智能体AI系统的隐私保证。

排序理由学术论文，介绍了一种用于多智能体LLM隐私的新框架。[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 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，介绍了一种用于多智能体LLM隐私的新框架。[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: 10 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Hengyu Wu, Blaise Delattre, Yang Cao · 2026-10-31 04:00

传播前判断：多智能体隐私的任务图上下文完整性

arXiv:2610.39532v1 Announce Type: cross Abstract: Multi-agent LLM systems increasingly rely on persistent memory and inter-agent communication. These capabilities create privacy risks that extend beyond individual interactions: a release appropriate in isolation may become inappr…

本文如何被排名

报道来源 [1]

传播前判断：多智能体隐私的任务图上下文完整性

相关实体

相关话题