DeepSeek-V4 Writeup Reveals Use of Agentic Trajectories in Mid-Training

cwolferesearch · x · 2026-08-06

A researcher discovered upon re-reading the DeepSeek-V4 writeup that the team incorporated a certain ratio of agentic trajectories into the mid-training phase.

Notably, this is the only sentence in the entire paper mentioning their mid-training process. The author notes that blending post-training data into mid-training—rather than just upsampling certain pretraining sources based on quality or grabbing domain-specific data—is becoming an industry standard practice.

Original post →

More from Research

Research channel →