无需训练，通过两个草稿一致性判断自动分配推理预算
DART: Draft-Agreement Routing for Training-Free Adaptive Thinking Budgets in Hybrid Reasoning Models
- 用两个低成本草稿判断是否直接回答，一致则跳过推理
- 草稿不一致时根据熵值预测所需推理长度，最高提升22.5分准确率
- 适用于0.6B到32B模型，无需标签数据或梯度更新
混合推理模型可选择直接回答或消耗额外标记进行深入思考。理想的路由器应为每个查询动态选择模式，让简单问题避免冗余推理，复杂问题获得足够计算资源。现有方法通常需要标注训练数据或固定推理预算，忽视模型自身答案层面的证据。我们提出DART，一种无需训练的路由框架：采样两个低成本的无思考草稿，当两者一致时直接回答；不一致时根据草稿熵值预测推理预算。在主要对比中，DART在多数设置下保持或提升全量推理的准确率，同时减少思考标记使用。在奥数数学任务上准确率最高提升9.0点，在代码任务上基于执行等价性测试提升22.5点，思考标记消耗降低32%-73%。第一阶段信号在0.6B至32B模型规模、不同模型族及仅提供API的服务环境下均有效，无需标注数据或梯度更新。代码已开源。
原文摘要 · Abstract (English)
Hybrid reasoning models can answer directly or spend extra tokens on extended thinking. A practical router should choose between these modes for each query, so easy problems avoid unnecessary reasoning and hard problems receive enough budget to finish the answer. Existing routers move in this direction, but they typically require labeled training data or fix thinking budgets up front, ignoring answer-level evidence from the model itself. We introduce DART, a training-free routing framework that samples two cheap no-think drafts, accepts direct answering when the drafts agree, and predicts a thinking budget from draft entropy when they disagree. Across the main comparisons, DART preserves or improves always-thinking accuracy in most settings while reducing thinking-token use. Accuracy improves by up to +9.0 points on Olympiad-level math and by up to +22.5 points on code under execution-based equivalence, while thinking-token use drops by 32-73%. The Stage~1 signal extends across model scales (0.6B--32B), model families, and API-only hosted settings, with no labeled data and no gradient updates required. Our code is available at https://github.com/js-lee-AI/DART.
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。