Unverified50% confidenceFactExact time
The policy trained by SPLIT-RL is used during inference in the same way as an ordinary GRPO model, requiring only a single CoT call and adding no inference cost.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedEach RL training step requires running inference (generating rollouts) and backpropagation (updating weights) simultaneously, making the compute requirements far higher than ordinary fine-tuning.73% similarUnverifiedThe core idea of SPLIT-RL is to separate the training of visual reasoning and language reasoning into two non-overlapping stages.72% similarUnverifiedJustGRPO的核心修复方案是在自回归顺序下训练GRPO，推理阶段保持并行解码72% similarVerifiedAt the training level, reasoning-enhanced models typically leverage reinforcement learning algorithms such as GRPO (Group Relative Policy Optimization), using the correctness of the final answer as the reward signal70% similarUnverifiedModern reasoning models generally use RLHF or its variant RLAIF for alignment training, where the model learns during training when to stop reasoning and when to output an answer.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990749API
curl https://kongchang.com/api/v1/knowledge/claims/990749MCP
get_claim(id=990749)