Model techniques map
Techniquespost-trainingreward modelling

specific method · filed under post-training

Web-development reward with deterministic checks and model judging

Combines deterministic functional and visual checks with internal reward-model judging for web-development tasks.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

Rewards consist of two components: deterministic checks and model judging by an internal reward model. Deterministic checks functionally test application behavior, and score structural and pixel-level similarity for tasks that replicate a reference.

usedunclearin Kimi K3Moonshot AI

Filed alongside

Other methods under post-training :: reward modelling.