Verified65% confidenceFactExact time

DeepSeek-R1通过在代码和数学两个可验证域上大规模运行GRPO算法取得成功

3

Sources

65%

Confidence

Long-term

Relevance

7/18/2026

First Seen

Sources

Cursor递归自进化：让模型训练下一代模型的完整路径

Related Claims

UnverifiedDeepSeek R1通过GRPO算法仅用ORM即可涌现出长程推理能力85% similar UnverifiedDeepSeek探索了GRPO算法，作为对RLHF原始框架的改进尝试83% similar VerifiedGRPO由DeepSeek团队系统化提出并在训练DeepSeek-R1系列模型时得到大规模验证80% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/550180

API

curl https://kongchang.com/api/v1/knowledge/claims/550180

MCP

get_claim(id=550180)