ambiguous · filed under post-training
Post-training optimization
A general reference to optimization after pretraining, without evidence specifying its algorithm or stages.
- source
- 1
- models
- 3
- 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.
With post-training optimization, the new model achieves major improvements in tool usage and intelligent agent tasks
usedpost trainingin DeepSeek-V3.1DeepSeek
Filed alongside
Other methods under post-training.
Scalable RL at Agent ScaleReinforcement learning for low-pass-rate tasksScalable reinforcement learning post-trainingSFT followed by RL and on-policy distillationExtended post-trainingJoint SFT and RLPost-training on diverse domainsThree-stage post-training with multi-teacher on-policy distillationThree-stage Thinker post-training strategy