Unverified50% confidenceFactExact time
Anthropic提出了RLAIF和Constitutional AI，DeepSeek探索了GRPO算法，都是对RLHF原始框架的改进
1
Sources
50%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
BAML：专为AI Agent设计的类型安全编程语言
Related Claims
UnverifiedDeepSeek explored the GRPO algorithm as an attempt to improve upon the original RLHF framework.84% similarVerifiedDeepSeek-R1 achieved success by running the GRPO algorithm at scale on two verifiable domains: code and mathematics.72% similarVerifiedGRPO (Group Relative Policy Optimization), proposed by DeepSeek, requires no separate training of a value network and has become the mainstream algorithm choice for current agentic RL training.67% similarUnverifiedGRPO和GSPO均是PPO算法的改进变体，DeepSeek-R1凭借GRPO在推理能力上实现大幅跃升67% similarUnverifiedDeepSeek R1 achieves emergent long-range reasoning capabilities using only an ORM through the GRPO algorithm.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/561430API
curl https://kongchang.com/api/v1/knowledge/claims/561430MCP
get_claim(id=561430)