按年被提到
20252025 · 5 次2026
大模型与语言模型›大模型推理与思维链·arXiv:2505.03335 · cs.LG

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Andrew Zhao, Yiran Wu, Yang Yue, Tong Wu, Quentin Xu, Yang Yue, Matthieu Lin, Shenzhi Wang, Qingyun Wu, Zilong Zheng, Gao Huang · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 6 人首次 2025-05-07 · 最近 2026-02-06
6不同的人
2活跃月份
6讨论串
77被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rewards. Recent RLVR works that operate under the zero setting avoid supervision in labeling the reasoning process, but still depend on manually curated collections of questions and answers for training. The scarcity of high-quality, human-produced examples raises concerns about the long-term scalability of relying on human supervision, a challenge already evident in the domain of language model pretraining. Furthermore, in a hypothetical future where AI surpasses human intelligence, tasks provided by humans may offer limited learning potential for a superintelligent system. To address these concerns, we propose a new RLVR paradigm called Absolute Zero, in which a single model learns to propose tasks that maximize its own learning progress and improves reasoning by solving them, without relying on any external data. Under this paradigm, we introduce the Absolute Zero Reasoner (AZR), a system that self-evolves its training curriculum and reasoning ability by using a code executor to both validate proposed code reasoning tasks and verify answers, serving as an unified source of verifiable reward to guide open-ended yet grounded learning. Despite being trained entirely without external data, AZR achieves overall SOTA performance on coding and mathematical reasoning tasks, outperforming existing zero-setting models that rely on tens of thousands of in-domain human-curated examples. Furthermore, we demonstrate that AZR can be effectively applied across different model scales and is compatible with various model classes.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论GorbachevyChase · 2026-02

“https://arxiv.org/abs/2505.03335 Check out the paper above on Absolute Zero. Language models don’t just repeat code they’ve seen. They can learn to code give the right training environment.”

We tasked Opus 4.6 using agent teams to build a C Compiler原评论 ↗
被提交为 story · 5 次