2 min lesson
Post-training pipeline end to end
Explain the order in "Post-training pipeline end to end", then say how you would verify the result.
Step 1 of 2
A state-of-the-art coding agent isn't one training run. It's a pipeline where each stage constrains the next and Cursor research owns decisions across all of them, including which base model to even start from.
Cursor has published that Composer 2Cursor's own coding model, built on the open Kimi K2.5 base as a software-engineering specialist. Cursor calls it frontier-level at coding and more cost-efficient than comparable models; Composer 2.5 has since replaced it in Cursor's model list. Press Enter for the full definition. continued pretraining on a code-heavy mix before any preference work, which is a real, defensible choice you can speak to. Composer 2.5The current Composer release, better at long-running tasks and at judging when a job needs a light touch versus deep work. Press Enter for the full definition., the model Cursor now serves, keeps that base and refines the rewards and data. Knowing the order of stages and what each one is good at lets you reason about where a problem you're handed actually lives.
Interactive diagram. Step through it with the Next and Previous controls below, or Tab to a region to read its detail.
Each stage constrains the next; RL is the optimization gate where reward, not imitation, takes over.