OrgAgent: Organize Your Multi-Agent System like a Company

TL;DR

OrgAgent introduces a hierarchical, company-style framework for multi-agent systems that improves reasoning performance and reduces token usage by structuring agents into governance, execution, and compliance layers.

Contribution

The paper proposes a novel hierarchical organization for multi-agent systems inspired by companies, demonstrating its advantages over flat structures in reasoning tasks.

Findings

Hierarchical multi-agent systems outperform flat ones in reasoning accuracy.

Hierarchy reduces token consumption significantly in large language model-based systems.

Stable skill assignment and layered verification benefit most from the hierarchical structure.

Abstract

While large language model-based multi-agent systems have shown strong potential for complex reasoning, how to effectively organize multiple agents remains an open question. In this paper, we introduce OrgAgent, a company-style hierarchical multi-agent framework that separates collaboration into governance, execution, and compliance layers. OrgAgent decomposes multi-agent reasoning into three layers: a governance layer for planning and resource allocation, an execution layer for task solving and review, and a compliance layer for final answer control. By evaluating the framework across reasoning tasks, LLMs, execution modes, and execution policies, we find that multi-agent systems organized in a company-style hierarchy generally outperform other organizational structures. Besides, hierarchical coordination also reduces token consumption relative to flat collaboration in most settings. For example, for GPT-OSS-120B, the hierarchical setting improves performance over flat multi-agent system by 102.73% while reducing token usage by 74.52% on SQuAD 2.0. Further analysis shows that hierarchy helps most when tasks benefit from stable skill assignment, controlled information flow, and layered verification. Overall, our findings highlight organizational structure as an important factor in multi-agent reasoning, shaping not only effectiveness and cost, but also coordination behavior.