PulseAugur
实时 07:30:18
English(EN) The Chase Is the Curriculum, the Capture Anchors the Credit: Pursuit-Evasion Self-Play for Zero-Data LLM Reasoning

新的LURE方法通过追逐-逃避游戏训练LLM进行推理

研究人员开发了一种名为LURE的新方法,用于在没有人类标注数据集的情况下训练大型语言模型(LLM)进行推理任务。该方法将训练过程构建为一场追逐-逃避游戏,其中一个LLM逃避者策略性地创建不同难度的任务,而一个LLM追逐者则尝试解决它们。该系统学会将任务设置在求解器成功率约为一半的难度级别,以优化“捕获前沿”奖励。与多个推理环境和LLM架构中的现有基线相比,该技术表现出优越的性能,实现了更强的分布外零样本准确率。 AI

影响 引入了一种新颖的LLM推理自玩训练范式,可能减少对人类标注数据的依赖。

排序理由 这是一篇详细介绍LLM训练新方法的学术论文。[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 →

新的LURE方法通过追逐-逃避游戏训练LLM进行推理

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是一篇详细介绍LLM训练新方法的学术论文。[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
3 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.CL TIER_1 English(EN) · Jing Yu, Shengchao Chen, Yiyun Tan ·

    追逐即课程,捕获即学分:用于零数据 LLM 推理的追逐-规避自玩

    arXiv:2608.21871v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards has become the dominant recipe for improving large language model reasoning, yet it presumes large human-curated task collections. Zero-data self-play removes this dependency, but exist…