根据任务复杂度动态选择模型规模，提升多智能体协作效率
Orchestrating Intelligence: Confidence-Aware Routing for Efficient Multi-Agent Collaboration across Multi-Scale Models
- 按推理阶段动态分配不同规模的模型，避免全程使用大模型
- 实验显示准确率最高提升12.88%，计算成本降低79.78%
- 适合需要高效推理的复杂任务场景，如多步规划与决策
尽管多智能体系统（MAS）在复杂推理任务中表现优于单智能体方法，但常面临显著的计算低效问题。现有框架通常在所有智能体角色中统一部署大语言模型（LLMs），未能考虑不同推理阶段的认知需求差异。为此，我们提出OI-MAS框架，一种新型多智能体系统，通过异构多尺度LLM池实现自适应模型选择策略。具体而言，OI-MAS引入状态依赖的路由机制，动态选择推理过程中的智能体角色与模型规模；同时，设计置信度感知机制，根据任务复杂度选择合适模型规模，减少对大规模模型的冗余依赖。实验结果表明，OI-MAS始终优于基线多智能体系统，在准确率上最高提升12.88%，计算成本最高降低79.78%。
原文摘要 · Abstract (English)
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\%.
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。