Kat-Dev-32B, Kat-Coder with Scalable Agentic RL

Kat-Dev-32B, Kat-Coder with Scalable Agentic RL(kwaipilot.github.io)

1 points by robert-zaremba 351 days ago | 1 comment

KAT-Dev-32B and KAT-Coder are optimized via several stages of training, including a mid-training stage, supervised fine-tuning (SFT) & reinforcement fine-tuning (RFT) stage and an large-scale agentic reinforcement learning (RL) stage.

robert-zaremba 351 days ago |

KAT-Dev-32B and KAT-Coder are optimized via several stages of training, including a mid-training stage, supervised fine-tuning (SFT) & reinforcement fine-tuning (RFT) stage and an large-scale agentic reinforcement learning (RL) stage.