[KongchangAI]
Unverified60% confidenceFactExact time

DeepSeek R1推理模型于2025年1月发布，采用基于规则奖励的强化学习训练策略（GRPO算法），并以MIT协议开源

2
Sources
60%
Confidence
Long-term
Relevance
7/6/2026
First Seen

Sources

Coze扣子入门教程：零代码搭建AI智能体完全指南
bilibiliAI大模型学习圈7/5/2026

Related Claims

UnverifiedDeepSeek-R1 was released in January 2025 and is focused on reasoning capabilities, trained with reinforcement learning, excelling at math and coding tasks.80% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/113630
API
curl https://kongchang.com/api/v1/knowledge/claims/113630
MCP
get_claim(id=113630)