让智能体在获取知识时自动遵守数据政策，防止违规访问。
Governance-Aware Vector Subscriptions for Multi-Agent Knowledge Ecosystems
- 将语义匹配与多维政策约束结合，实现合规的知识订阅。
- 在1000段文本上验证，完全符合五类政策要求且不漏发授权内容。
- 适合需要遵守欧盟数据法规的多智能体系统开发者使用。
随着人工智能代理生态系统的扩展，代理需要实时监控相关知识。语义发布-订阅系统通过向量订阅匹配新内容来解决这一问题。但在多代理环境中，各代理遵循不同的数据处理策略，无限制的语义订阅会导致政策违规：代理接收到其无权访问的内容通知。本文提出治理感知的向量订阅机制，将语义相似性匹配与基于监管框架（欧盟《数字市场法案》、欧盟《人工智能法案》）的多维政策谓词相结合。政策谓词涵盖五个独立维度：处理层级、直接营销限制、训练退出权、管辖区域和科学用途，每个维度具有不同法律依据。代理订阅经过筛选的知识库语义区域；仅当内容同时满足相似度阈值和所有适用政策约束时才发送通知。我们形式化该机制，并在AIngram（一个运行中的多代理知识库）中实现，使用PASA基准进行评估。在合成语料库（1000个片段，93个订阅，5个领域）上验证，受控模式正确执行所有政策约束，同时保留授权内容的传递。对五个政策维度的消融实验表明，任一单一维度均不足以实现完全合规。
原文摘要 · Abstract (English)
As AI agent ecosystems grow, agents need mechanisms to monitor relevant knowledge in real time. Semantic publish-subscribe systems address this by matching new content against vector subscriptions. However, in multi-agent settings where agents operate under different data handling policies, unrestricted semantic subscriptions create policy violations: agents receive notifications about content they are not authorized to access. We introduce governance-aware vector subscriptions, a mechanism that composes semantic similarity matching with multi-dimensional policy predicates grounded in regulatory frameworks (EU DSM Directive, EU AI Act). The policy predicate operates over multiple independent dimensions (processing level, direct marketing restrictions, training opt-out, jurisdiction, and scientific usage) each with distinct legal bases. Agents subscribe to semantic regions of a curated knowledge base; notifications are dispatched only for validated content that passes both the similarity threshold and all applicable policy constraints. We formalize the mechanism, implement it within AIngram (an operational multi-agent knowledge base), and evaluate it using the PASA benchmark. We validate the mechanism on a synthetic corpus (1,000 chunks, 93 subscriptions, 5 domains): the governed mode correctly enforces all policy constraints while preserving delivery of authorized content. Ablation across five policy dimensions shows that no single dimension suffices for full compliance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。