探索多智能体协作推理的结构设计，提升专家分工与协同效率。
Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study
- 按领域匹配专家能力，提升上下文推理效果
- 融合多元知识比固定任务分解更有效
- 规模扩展需平衡性能与通信开销
设计高效多智能体大模型系统的协作结构以增强集体推理能力至关重要，但目前仍缺乏深入研究。本文系统探究三个关键设计维度对协作推理性能的影响：(1) 专家领域匹配度，(2) 协作模式（结构化流程 vs. 多样性驱动整合），(3) 系统规模。研究发现，专家匹配度的收益高度依赖任务领域，在上下文推理任务中表现最佳；而聚焦于整合多样化知识的协作方式，始终优于僵化的任务分解模式。此外，我们实证分析了通过专业化实现系统规模扩展的影响，揭示出通信协议效率是可扩展推理的关键瓶颈。本工作为配置专用多智能体系统提供了具体指导，并识别出可扩展推理中的核心架构权衡与瓶颈。代码将在论文接受后公开。
原文摘要 · Abstract (English)
Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically investigate how collaborative reasoning performance is affected by three key design dimensions: (1) Expertise-Domain Alignment, (2) Collaboration Paradigm (structured workflow vs. diversity-driven integration), and (3) System Scale. Our findings reveal that expertise alignment benefits are highly domain-contingent, proving most effective for contextual reasoning tasks. Furthermore, collaboration focused on integrating diverse knowledge consistently outperforms rigid task decomposition. Finally, we empirically explore the impact of scaling the multi-agent system with expertise specialization and study the computational trade off, highlighting the need for more efficient communication protocol design. This work provides concrete guidelines for configuring specialized multi-agent system and identifies critical architectural trade-offs and bottlenecks for scalable multi-agent reasoning. The code will be made available upon acceptance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。