Unverified80% confidenceFactTime unknown

开源社区对o1的复现尝试包括DeepSeek-R1和QwQ，通过强化学习训练模型的推理过程是实现类似能力的关键路径

1

Sources

80%

Confidence

Long-term

Relevance

6/1/2026

First Seen

Sources

GitHub 8K Star：最全LLM大模型资源宝库深度解析

githubWangRongsheng

Related Entities

DeepSeek-R1model QwQmodel

Related Claims

UnverifiedDeepSeek-R1、Qwen的QwQ等开源模型在积极探索类似o1的推理增强路线81% similar UnverifiedDeepSeek-R1和Qwen-QwQ等开源模型在推理增强（思维链推理）方向上取得了显著进展80% similar Unverifiedo1模型的成功启发了DeepSeek-R1、Qwen-QwQ等开源复现工作79% similar UnverifiedDeepSeek-R1和Qwen系列模型都公开讨论过代码即奖励训练范式的有效性78% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/32638

API

curl https://kongchang.com/api/v1/knowledge/claims/32638

MCP

get_claim(id=32638)