How do we coordinate millions of AI agents without chaos?

Bang Liu, Yongfeng Gu, Jiayi Zhang, Zhaoyang Yu, Sirui Hong, Maojia Song, Xiaoqiang Wang, Mingyi Deng, Zijie Zhuang, Ronghao Wang, Mingzhe Cao, Yutong Zhu, Xingjian Li, Yifan Wu, Jianhao Ruan, Yiran Peng, Shuangrui Chen, Jinlin Wang, Yizhang Lin, Dongjie Zhang, Dekun Wu, Chen Ma, Lizi Liao, Han Yu, Jian Pei, Heng Ji, Qiang Yang, Yuyu Luo, Chenglin Wu

As AI agents move from tools into critical infrastructure—managing systems, executing transactions, interacting with each other—the real bottleneck isn't model capability but coordination. This paper proposes Foundation Protocol, a graph-based layer that treats heterogeneous agents, humans, institutions, and tools as unified entities. It bundles economic primitives (metering, receipts, settlement) with policy and audit trails, designed to wrap existing systems incrementally. The goal: enable composable autonomous agency without sacrificing accountability or governability as AI systems scale into social infrastructure.