让大模型自动判断该用简单还是复杂推理，省资源又不丢精度。
Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning
- 通过隐藏层特征估算模型能力，动态切换推理模式。
- 在多个基准上减少30%-55%的令牌消耗，精度不变。
- 适配不同规模模型，实用性强，适合部署优化场景。
尽管增强推理的大语言模型（RLLMs）通过延长推理链显著提升了复杂任务表现，但对简单问题也进行深度推理导致大量无谓的令牌消耗。为解决此问题，我们提出Self-Route，一种基于模型能力估计的动态推理框架，可自动在通用模式与推理模式间切换。该方法引入轻量级预推理阶段，从隐藏层表示中提取能力感知嵌入，实现实时评估模型解题能力。我们进一步构建了基于难度估计的Gradient-10K数据集，采用密集复杂度采样以训练路由器实现精准的能力边界检测。大量实验表明，Self-Route在保持与推理模型相当精度的同时，跨多种基准将令牌消耗降低30%-55%。该框架在不同参数规模和推理范式下均表现稳健，展现出强泛化性与实际应用价值。
原文摘要 · Abstract (English)
While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems where Short Chain-of-Thought (Short CoT) suffices. This overthinking phenomenon leads to inefficient resource usage without proportional accuracy gains. To address this issue, we propose Self-Route, a dynamic reasoning framework that automatically selects between general and reasoning modes based on model capability estimation. Our approach introduces a lightweight pre-inference stage to extract capability-aware embeddings from hidden layer representations, enabling real-time evaluation of the model's ability to solve problems. We further construct Gradient-10K, a model difficulty estimation-based dataset with dense complexity sampling, to train the router for precise capability boundary detection. Extensive experiments demonstrate that Self-Route achieves comparable accuracy to reasoning models while reducing token consumption by 30-55\% across diverse benchmarks. The proposed framework demonstrates consistent effectiveness across models with different parameter scales and reasoning paradigms, highlighting its general applicability and practical value.
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。