specific method · filed under post-training
Post-training on diverse domains
Post-training on a broad mix of domains, including math, agentic code and tool use, audio, image, chat, and safety.
- 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 post-trained Inkling on a broad distribution of math, agentic code & tool use, audio, image, chat, and safety domains.
usedpost trainingin InklingThinking Machines Lab
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 optimizationThree-stage post-training with multi-teacher on-policy distillationThree-stage Thinker post-training strategy