递归推理新方法，用极少算力达到顶尖数学解题效果
MatryoshkaThinking: Recursive Test-Time Scaling Enables Efficient Reasoning
- 通过递归利用模型的推理、验证和摘要能力，提升解题正确率
- 在AIME2025上达99.79分，仅需DeepConf4%的计算量
- 适合追求高效推理的开发者与部署场景
测试时扩展已成为语言建模中一种有前景的范式，即在推理阶段分配更多计算资源以提升模型性能。近期方法如DeepConf已证明该策略的有效性，但通常伴随显著的计算开销。本文提出MatryoshkaThinking，一种显著降低计算成本同时保持顶级性能的新方法。其核心在于递归利用模型内在的推理、验证与摘要能力，共同增强正确解的保留，并缩小Pass@k与Pass@1之间的差距。在多个开源模型及挑战性多模态推理基准上的全面评估验证了该方法的有效性与通用性。研究为先进语言模型的高效可扩展测试时推理策略设计提供了新思路。
原文摘要 · Abstract (English)
Test-time scaling has emerged as a promising paradigm in language modeling, wherein additional computational resources are allocated during inference to enhance model performance. Recent approaches, such as DeepConf, have demonstrated the efficacy of this strategy, however, they often incur substantial computational overhead to achieve competitive results. In this work, we propose MatryoshkaThinking, a novel method that significantly reduces computational cost while maintaining state-of-the-art performance. Specifically, MatryoshkaThinking attains a score of 99.79 on AIME2025 using only 4% of the computation required by DeepConf. The core of our approach lies in the recursive exploitation of the model's intrinsic capabilities in reasoning, verification, and summarization, which collectively enhance the retention of correct solutions and reduce the disparity between Pass@k and Pass@1. Comprehensive evaluations across multiple open-source models and challenging multi-modal reasoning benchmarks validate the effectiveness and generality of our method. These findings offer new insights into the design of efficient and scalable test-time inference strategies for advanced language 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。