提出Min-Seek方法，让大模型推理更长且稳定，无需调参。
Thinking Long, but Short: Stable Sequential Test-Time Scaling for Large Reasoning Models
- 通过动态编码关键键值对，实现超长推理而不增加缓存开销。
- 在多种任务上显著提升准确率，且推理长度越长效果越好。
- 适合需要高精度长推理的应用，如复杂数学题或法律分析。
序列测试时缩放是一种有前景的无训练方法，可提升大型推理模型的准确性，但当前实现存在显著局限。延长推理过程虽能提高准确率，但进一步延长会导致准确率下降和模型不稳定。本文提出一种新型序列测试时缩放方法——Min-Seek，可在广泛诱导推理长度下显著提升模型准确率，稳定序列缩放性能，并消除对推理长度微调的需求。该方法本质上高效：推理过程中仅需在键值缓存中保留一个额外推理步骤的键值对。通过自定义键值缓存，存储键而不带位置嵌入，并在每次生成新推理前动态连续编码，该方法可使模型在超出最大上下文长度的情况下仍持续良好推理，且在温和条件下具有线性计算复杂度。
原文摘要 · Abstract (English)
Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their accuracy, but as the length of reasoning is further extended, it has also been shown to result in accuracy degradation and model instability. This work presents a novel sequential test-time scaling method, Min-Seek, which improves model accuracy significantly over a wide range of induced thoughts, stabilizing the accuracy of sequential scaling, and removing the need for reasoning length fine-tuning. Beyond improving model accuracy over a variety of reasoning tasks, our method is inherently efficient, as only the KV pairs of one additional induced thought are kept in the KV cache during reasoning. With a custom KV cache which stores keys without position embeddings, by dynamically encoding them contiguously before each new generated thought, our method can continue to reason well beyond a model's maximum context length, and under mild conditions has linear computational complexity.
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。