Model techniques map
Techniquespost-trainingreinforcement learning algorithm

specific method · filed under post-training

GSPO

A named RL method adopted with rule-based rewards to improve capability and training stability; the evidence does not expand the acronym.

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.

we incorporate rule-based rewards and adopt GSPO (Zheng et al., 2025) to further improve overall capability and training stability across diverse tasks.

usedpost trainingin Qwen3.5-OmniQwen

Filed alongside

Other methods under post-training :: reinforcement learning algorithm.