English(EN) Steer, Don't Tell: Breaking Reasoning Plateaus with Reachability-Aligned Self-Distillation

新的自引导推理器方法改进了大型语言模型的解决问题能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-04 05:00

研究人员开发了一种名为自引导推理器（SSR）的新方法，以提高大型语言模型在复杂问题上的推理能力，尤其是在缺乏专家指导的情况下。SSR通过确保自生成的训练数据与模型实际可达到的动作对齐，而不是依赖于可能格式错误或无法达到的专家轨迹，来解决“解条件化”问题。这种方法显示出显著的改进，恢复了先前无法解决的74%以上问题的正确轨迹，并将AIME25/26和HMMT26等具有挑战性的数学竞赛的总体准确率提高了4.9个百分点。 AI

影响增强了大型语言模型在专家数据稀缺的复杂推理任务上的能力，有可能提高在数学和编码等领域的表现。

排序理由详细介绍大型语言模型推理新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 43 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍大型语言模型推理新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Zijian Wu, Lingkai Kong, Lin Yang, Haiteng Zhao, Kuikun Liu, Kai Chen, Dahua Lin, Wenwei Zhang · 2026-11-04 05:00

引导而非告知：通过可达性对齐的自蒸馏打破推理瓶颈

arXiv:2611.00796v1 Announce Type: new Abstract: Post training for large reasoning models remains insufficient on challenging problems, whose correct trajectories are hard to sample. Though prior works address this difficulty by integrating supervised fine tuning on expert traject…

本文如何被排名

报道来源 [1]

引导而非告知：通过可达性对齐的自蒸馏打破推理瓶颈

相关实体

相关话题