# Governance-Aware Vector Subscriptions for Multi-Agent Knowledge Ecosystems

arXiv: https://arxiv.org/abs/2603.20833 · HTML: https://mlsanity.com/paper/2603.20833/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 19 references that are in the map.
- First posted on arXiv 21 Mar 2026.

## Builds on (most cited first, 6 of 6)

- [Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control](https://mlsanity.com/paper/2505.18279/) (2025)
- [The Rise of AI Agent Communities: Large-Scale Analysis of Discourse and Interaction on Moltbook](https://mlsanity.com/paper/2602.12634/) (2026)
- [Harnessing the power of LLMs for normative reasoning in MASs](https://mlsanity.com/paper/2403.16524/) (2024)
- [Federation of Agents: A Semantics-Aware Communication Fabric for Large-Scale Agentic AI](https://mlsanity.com/paper/2509.20175/) (2025)
- [Policy Cards: Machine-Readable Runtime Governance for Autonomous AI Agents](https://mlsanity.com/paper/2510.24383/) (2025)
- [SAMEP: A Secure Protocol for Persistent Context Sharing Across AI Agents](https://mlsanity.com/paper/2507.10562/) (2025)

## Built on by (most cited first, 1 of 1)

- [Deliberative Curation: A Protocol for Multi-Agent Knowledge Bases](https://mlsanity.com/paper/2606.00007/) (2026)

## Abstract (arXiv)

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.