根据题目难度选最合适的模型，省钱又不丢精度。
Optimizing Reasoning Efficiency through Prompt Difficulty Prediction
- 用轻量级预测器判断题目难易，动态分配最小适用模型。
- 在多个数学基准上，效率比随机分配高，性能接近32B大模型。
- 适合需要低成本部署复杂推理模型的场景。
推理型语言模型在复杂任务上表现优异，但因规模大、推理路径长，部署成本高昂。本文提出一种路由方法，将每个问题分配给最可能解决它的最小模型，从而降低计算开销而不牺牲准确性。利用s1.1-32B模型生成的中间表示，训练轻量级预测器以判断题目难度或模型正确性，指导在一组推理模型间的路由决策。在多个数学基准测试中，该路由策略相较于随机分配显著提升效率，并保持与s1.1-32B相当的性能，同时大幅减少计算资源消耗。结果表明，基于难度感知的路由对推理模型的成本高效部署具有显著有效性。
原文摘要 · Abstract (English)
Reasoning language models perform well on complex tasks but are costly to deploy due to their size and long reasoning traces. We propose a routing approach that assigns each problem to the smallest model likely to solve it, reducing compute without sacrificing accuracy. Using intermediate representations from s1.1-32B, we train lightweight predictors of problem difficulty or model correctness to guide routing across a pool of reasoning models. On diverse math benchmarks, routing improves efficiency over random assignment and matches s1.1-32B's performance while using significantly less compute. Our results demonstrate that difficulty-aware routing is effective for cost-efficient deployment of reasoning models.
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。