specific method · not yet filed
RL training with more environments, diverse tasks, and compute
- 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.
more environments, more diverse tasks, and more compute spent training on them
usedpost trainingin GLM-5.3Z.ai