While multi-agent systems (MAS) have demonstrated superior performance over single-agent approaches in complex reasoning tasks, they often suffer from significant computational inefficiencies. Existing frameworks typically deploy large language models (LLMs) uniformly across all agent roles, failing to account for the varying cognitive demands of different reasoning stages. We address this inefficiency by proposing OI-MAS framework, a novel multi-agent framework that implements an adaptive model-selection policy across a heterogeneous pool of multi-scale LLMs. Specifically, OI-MAS introduces a state-dependent routing mechanism that dynamically selects agent roles and model scales throughout the reasoning process. In addition, we introduce a confidence-aware mechanism that selects appropriate model scales conditioned on task complexity, thus reducing unnecessary reliance on large-scale models. Experimental results show that OI-MAS consistently outperforms baseline multi-agent systems, improving accuracy by up to 12.88\% while reducing cost by up to 79.78\%.

翻译：尽管多智能体系统在复杂推理任务中展现出优于单智能体方法的性能，但其通常存在显著的计算效率低下问题。现有框架通常在所有智能体角色中统一部署大规模语言模型，未能考虑不同推理阶段认知需求的差异性。为应对这一效率瓶颈，我们提出OI-MAS框架——一种创新的多智能体框架，通过在异构多尺度LLM池中实施自适应模型选择策略来实现优化。具体而言，OI-MAS引入了状态依赖的路由机制，能够在推理过程中动态选择智能体角色与模型规模。此外，我们提出置信度感知机制，可根据任务复杂度选择适配的模型规模，从而减少对大规模模型的不必要依赖。实验结果表明，OI-MAS在多个基准测试中持续优于基线多智能体系统，在最高提升12.88%准确率的同时，将计算成本降低达79.78%。