SynapseRoute：一种面向双状态大语言模型的自动路由切换框架
SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model
AI总结：
SynapseRoute提出基于机器学习的动态路由框架，根据问题复杂度在思考与非思考模式间自动切换，在医学问答中提升准确率的同时显著降低推理时间和token消耗。
摘要：
随着大语言模型（LLMs）在实际应用中的广泛采用，选择合适的模型不仅需要平衡性能，还需要考虑运行成本。具备推理能力的模型的出现进一步拉大了“思考”（高推理）模式与“非思考”（快速、低成本）模式之间的成本差距。在本工作中，我们揭示出大约58%的医学问题可以仅由非思考模式准确回答，而无需高成本的推理过程。这凸显了问题复杂性上存在的明显二分性，并表明基于复杂性将查询动态路由到合适模式可以优化准确性、成本效益和整体用户体验。基于此，我们进一步提出SynapseRoute，一个基于机器学习的动态路由框架，能够智能地将输入查询分配到思考模式或非思考模式。在多个医学数据集上的实验结果表明，与仅使用思考模式相比，SynapseRoute不仅提高了整体准确性（0.8390 vs. 0.8272），还将推理时间减少了36.8%，并将token消耗减少了39.66%。重要的是，定性分析表明，对较简单查询进行过度推理可能导致不必要的延迟，甚至降低准确性，而我们的自适应路由避免了这一缺陷。最后，本工作进一步引入Accuracy-Inference-Token（AIT）指标，以综合评估准确性、延迟和token成本之间的权衡。
英文摘要：
With the widespread adoption of large language models (LLMs) in practical applications, selecting an appropriate model requires balancing not only performance but also operational cost. The emergence of reasoning-capable models has further widened the cost gap between "thinking" (high reasoning) and "non-thinking" (fast, low-cost) modes. In this work, we reveal that approximately 58% of medical questions can be accurately answered by the non-thinking mode alone, without requiring the high-cost reasoning process. This highlights a clear dichotomy in problem complexity and suggests that dynamically routing queries to the appropriate mode based on complexity could optimize accuracy, cost-efficiency, and overall user experience. Based on this, we further propose SynapseRoute, a machine learning-based dynamic routing framework that intelligently assigns input queries to either thinking or non-thinking modes. Experimental results on several medical datasets demonstrate that SynapseRoute not only improves overall accuracy (0.8390 vs. 0.8272) compared to the thinking mode alone but also reduces inference time by 36.8% and token consumption by 39.66%. Importantly, qualitative analysis indicates that over-reasoning on simpler queries can lead to unnecessary delays and even decreased accuracy, a pitfall avoided by our adaptive routing. Finally, this work further introduces the Accuracy-Inference-Token (AIT) index to comprehensively evaluate the trade-offs among accuracy, latency, and token cost.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
