English(EN) G-Zero: Self-Play for Open-Ended Generation from Zero Data

G-Zero框架使LLM能够在无外部数据的情况下自我演进

作者 PulseAugur 编辑部 · [1 个来源] · 2026-05-11 04:12

研究人员推出了一种新颖的框架G-Zero，用于在大型语言模型中进行开放式生成，而无需依赖外部裁判或预先存在的数据。该系统采用一种协同进化方法，其中一个Proposer模型生成具有挑战性的查询和提示，而一个Generator模型则根据这些自我生成的指南学习改进其响应。这种由称为Hint-$\delta$的内在奖励信号驱动的方法，旨在克服代理LLM裁判的局限性，并使模型在复杂、不可验证的领域中能够持续自我演进。 AI

影响引入了一种新颖的LLM自我改进方法，有可能实现更自主和可扩展的模型开发。

排序理由发表了一篇详细介绍新AI框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 发表了一篇详细介绍新AI框架的学术论文。[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: 183 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]

arXiv cs.AI TIER_1 English(EN) · Jiaxin Huang · 2026-05-11 04:12

G-Zero：从零数据开始的开放式生成自玩

Self-evolving LLMs excel in verifiable domains but struggle in open-ended tasks, where reliance on proxy LLM judges introduces capability bottlenecks and reward hacking. To overcome this, we introduce G-Zero, a verifier-free, co-evolutionary framework for autonomous self-improvem…

本文如何被排名

报道来源 [1]

G-Zero：从零数据开始的开放式生成自玩

相关话题