Unverified50% confidenceFactExact time
Agima's training is divided into two stages: the first stage uses supervised fine-tuning (SFT) to unify the policy and the world model into a single omni-model; the second stage uses agentic reinforcement learning (RL) to teach the model to reason over imagined futures and use them for planning.
1
Sources
50%
Confidence
Long-term
Relevance
10/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedModels trained with reinforcement learning (RL) outperform models trained solely with SFT on Agent tasks.74% similarVerifiedLarge model training goes through three core stages: pre-training, supervised fine-tuning (SFT), and preference alignment.74% similarUnverifiedPistis's training pipeline is divided into two stages: the first stage is large-scale multimodal supervised fine-tuning (SFT), and the second stage is Interleaved Distillation and Reinforcement Learning (IDRL).73% similarUnverifiedTRACER employs a two-stage training process: the first stage performs supervised fine-tuning (SFT) on real user conversations, and the second stage introduces multi-turn reinforcement learning (RL).72% similarVerifiedThe three-stage alignment training paradigm of SFT–reward model–RLHF was first systematically proposed by OpenAI in the InstructGPT paper.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1073373API
curl https://kongchang.com/api/v1/knowledge/claims/1073373MCP
get_claim(id=1073373)