The Year in AI Papers
The year/Independent research

Paper 2605.23218

Foundation Protocol: A Coordination Layer for Agentic Society

Bang Liu, Yongfeng Gu, Jiayi Zhang, Zhaoyang Yu, Sirui Hong, Maojia Song, Xiaoqiang Wang, Mingyi Deng, Zijie Zhuang, Ronghao Wang, Mingzhe Cao, Yutong Zhu, et al.

Published
May 2026
Research lab
Independent
Citations
0
GitHub
52 stars

01 In brief

Summary

The Foundation Protocol (FP) is a graph-first coordination layer for an emerging human-AI society, designed to unify heterogeneous entities (agents, tools, humans, institutions, organizations) and support multi-party organization, event-based collaboration, economic primitives (metering, receipts, settlement), and first-class policy, provenance, and audit.

FP's architecture comprises four planes: Entity & Trust, Transport & Routing, Interaction & Organization, and Regulation & Oversight, plus a configuration/profile plane.

It aims to complement existing protocols (MCP, A2A, A2UI, DIDComm, ANP, UCP) rather than replace them, enabling incremental adoption.

The paper includes a detailed scenario of an AI company with human oversight, demonstrating all planes.

The reference implementation (foundation-protocol and ai-link-net) provides a Python runtime with a tree topology, checkpoint-based access control, human-in-the-loop approval, protocol bridges (CLI adapter, MCP), a contract lifecycle with escrow/direct payment modes, and a reputation system derived from contract evidence.

FP's design principles include keeping the core small, progressive disclosure, explicit multi-party interaction, and treating evidence as a first-class output.

02 From the paper

Abstract

Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly interact with one another. As these systems scale, the bottleneck shifts away from raw model capability toward coordination. Agents need to form reliable relationships, organize multi-agent work, exchange value, support an AI economy, and stay safe and accountable under real-world oversight. This paper introduces the Foundation Protocol (FP), a graph-first coordination layer for an emerging human-AI society. FP unifies heterogeneous entities, including agents, tools, resources, humans, institutions, and organizations, and supports native multi-party organization and event-based collaboration. It also provides economic primitives for metering, receipts, and settlement, and treats policy, provenance, and audit as first-class concerns. FP is designed to wrap and bridge existing protocols rather than replace them, enabling incremental adoption while reducing integration and governance overhead. The aim is to keep autonomous agency composable while keeping accountability non-negotiable, so that coordination itself can become shared infrastructure for a human-AI society that is open, pluralistic, and governable.