Model techniques map
Techniquespost-trainingreinforcement learning algorithm

implementation detail · filed under post-training

Agentic RL Task Mix

An RL prompt distribution spanning code-repository, shell, and tool-integrated math tasks using a shared tool-use API.

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.

The RL prompt distribution spans three families that share a single tool-use API.

useddata curationin LAGUNA M.1/XS.2Poolside

Filed alongside

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