智能路由选择让多模型协作更高效，动态匹配最佳助手。
Optimal-Agent-Selection: State-Aware Routing Framework for Efficient Multi-Agent Collaboration
- 根据任务状态和历史交互，动态选最优单个代理协作。
- 在复杂推理任务上提升23.8%，数据收集成本降低90.1%。
- 适合需要高效多模型协同的复杂任务系统设计者。
基于大语言模型的多代理系统在解决复杂任务方面展现出巨大潜力，能整合各异专家能力并灵活协作。然而，僵化的调度与低效协调策略限制了其性能。本文提出STRMAC，一种状态感知的路由框架，通过分别编码交互历史与代理知识，动态选择每步最合适的单一代理以实现高效协作。此外，引入自演化数据生成方法，加速高质量执行路径的收集。在多个挑战性协作推理基准测试中，该方法达到领先性能，相较基线最高提升23.8%，数据收集开销相比穷举搜索减少90.1%。
原文摘要 · Abstract (English)
The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse agents to integrate unique expertise, collaborate flexibly, and address challenges unattainable for individual models. However, the full potential of such systems is hindered by rigid agent scheduling and inefficient coordination strategies that fail to adapt to evolving task requirements. In this paper, we propose STRMAC, a state-aware routing framework designed for efficient collaboration in multi-agent systems. Our method separately encodes interaction history and agent knowledge to power the router, which adaptively selects the most suitable single agent at each step for efficient and effective collaboration. Furthermore, we introduce a self-evolving data generation approach that accelerates the collection of high-quality execution paths for efficient system training. Experiments on challenging collaborative reasoning benchmarks demonstrate that our method achieves state-of-the-art performance, achieving up to 23.8% improvement over baselines and reducing data collection overhead by up to 90.1% compared to exhaustive search.
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。