Model techniques map
Techniquespost-trainingreinforcement learning algorithm

ambiguous · filed under post-training

SAO with Compaction

An RL strategy identified as SAO with compaction; the evidence does not expand SAO or describe the mechanism.

Also called SAO with compaction (RL strategy).

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.

It carries over the RL strategies introduced in GLM-5.2, including SAO with compaction

usedoptimizationin GLM-5.3Z.ai

Filed alongside

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