OrgAgent: Organize Your Multi-Agent System like a Company

2026-04-01

AI Summary

This work proposes a hierarchical multi-agent framework inspired by corporate organizational structures to enhance the performance of large language models in complex reasoning tasks. The framework introduces three distinct layers: a governance layer for planning and resource allocation, an execution layer responsible for task execution and peer review, and a compliance layer that controls the final output. By incorporating corporate-style hierarchical mechanisms into multi-agent systems for the first time, the approach enables stable skill specialization, controllable information flow, and layered verification. Experimental results demonstrate that this method achieves a 102.73% performance improvement over flat architectures on benchmarks such as SQuAD 2.0 while reducing token consumption by 74.52%, thereby significantly balancing both efficiency and accuracy.

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.

Problem

• multi-agent system
• organizational structure
• hierarchical coordination
• complex reasoning
• agent collaboration

Innovation

• hierarchical multi-agent system
• company-style organization
• governance-execution-compliance framework
• token-efficient collaboration
• structured coordination