OrgAgent: 以公司式层级结构组织你的多智能体系统
OrgAgent: Organize Your Multi-Agent System like a Company
AI总结:
本文提出OrgAgent框架,通过治理、执行、合规三层结构提升多智能体系统的推理性能,实验显示层级结构在任务稳定性、信息控制和验证方面表现更优。
摘要:
尽管基于大语言模型的多智能体系统在复杂推理中展现出强大潜力,但如何有效组织多个智能体仍是一个开放问题。本文引入OrgAgent,一种公司式层级多智能体框架,将协作分为治理、执行和合规层。OrgAgent将多智能体推理分解为三层:治理层负责规划和资源分配,执行层负责任务解决和审查,合规层负责最终答案控制。通过在推理任务、LLM、执行模式和执行策略上评估该框架,我们发现以公司式层级结构组织的多智能体系统在大多数情况下均优于其他组织结构。此外,层级协调在大多数设置中也减少了token消耗。例如,对于GPT-OSS-120B,层级设置在SQuAD 2.0上比扁平多智能体系统提高了102.73%的性能,同时减少了74.52%的token使用。进一步分析表明,层级结构在任务受益于稳定技能分配、受控信息流和分层验证时效果最佳。总体而言,我们的发现强调了组织结构在多智能体推理中的重要性,不仅影响有效性与成本,还塑造协调行为。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。