paperSeptember 2026Unreviewed

OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets

Dongsheng Chen, Xiangyu Zhao, Xin Yao, Xuetao Wei

Abstract

AI agents powered by large language models are evolving from isolated assistants into heterogeneous systems in which multiple agents, planners, tools, and execution backends operate over shared environments. In such settings, safety becomes a system-level action-governance problem: deciding whether a pending action should be committed given policy-relevant state accumulated across a session. Existing safeguards operate at fragmented boundaries, making it difficult to enforce shared policies over

Cite

@misc{chen2026openagentflow,
  title = {{OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets}},
  author = {Dongsheng Chen and Xiangyu Zhao and Xin Yao and Xuetao Wei},
  year = {2026},
  month = sep,
  eprint = {2609.00015},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.00015}
}