Reproduce “Governance Gaps in Agent Interoperability Protocols: What MCP, A2A, and ACP Cannot Express” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Richard Kang, Yudho Diponegoro
DoiT International and an independent researcher systematically analyzed five prominent agent interoperability protocols against a six-dimension governance taxonomy, revealing a consistent and significant gap in native support for collective decision-making and community governance. The study concludes that current protocols primarily facilitate task coordination, underscoring the necessity for a dedicated architectural layer to enable enterprise-grade agent governance.
Key insights
- Agent community governance constitutes a missing architectural layer above current interoperability standards, rather than merely a set of features to be added within existing protocols.
- Primitives for critical governance functions like voting, dissent preservation, and human escalation are universally absent across all five analyzed protocols, highlighting a shared design philosophy focused on coordination over governance.
- Where partial support for membership or deliberation exists, it addresses coordination aspects (e.g., agent existence, bilateral message exchange) but lacks the robust, multilateral semantics required for formal community decision-making and governance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.