Existing Multi-Agent Systems (MAS) typically rely on static, homogeneous model configurations, limiting their ability to exploit the distinct strengths of differently post-trained models. To address this, we introduce Team-of-Thoughts, a novel MAS architecture that leverages the complementary capabilities of heterogeneous agents via an orchestrator-tool paradigm. Our framework introduces two key mechanisms to optimize performance: (1) an orchestrator calibration scheme that identifies models with superior coordination capabilities, and (2) a self-assessment protocol where tool agents profile their own domain expertise to account for variations in post-training skills. During inference, the orchestrator dynamically activates the most suitable tool agents based on these proficiency profiles. Experiments on five reasoning and code generation benchmarks show that Team-of-Thoughts delivers consistently superior task performance. Notably, on AIME24 and LiveCodeBench, our approach achieves accuracies of 96.67% and 72.53%, respectively, substantially outperforming homogeneous role-play baselines, which score 80% and 65.93%.

翻译：现有的多智能体系统通常依赖于静态、同质的模型配置，这限制了其利用不同后训练模型独特优势的能力。为解决这一问题，我们提出了思维团队，一种新颖的多智能体系统架构，通过编排器-工具范式利用异构智能体的互补能力。我们的框架引入了两个关键机制以优化性能：（1）一种编排器校准方案，用于识别具有卓越协调能力的模型；（2）一种自评估协议，工具智能体通过该协议分析其自身领域专长，以考虑后训练技能差异。在推理过程中，编排器根据这些能力配置文件动态激活最合适的工具智能体。在五个推理和代码生成基准测试上的实验表明，思维团队始终提供卓越的任务性能。值得注意的是，在AIME24和LiveCodeBench上，我们的方法分别实现了96.67%和72.53%的准确率，显著优于同质角色扮演基线（其得分分别为80%和65.93%）。